Daily Papers

Detecting factual inconsistencies in summarization is critical, yet existing benchmarks lack the necessary challenge and interpretability for robust evaluation. In this paper, we introduce SummExecEdit, a novel benchmark leveraging executable edits to assess models on their ability to both detect factual errors and provide accurate explanations. The top-performing model, Claude3-Opus, achieves a joint detection and explanation score of only 0.49 in our benchmark, with individual scores of 0.67 for detection and 0.73 for explanation. Furthermore, we identify four primary types of explanation errors, with 45.4% of errors focusing on completely unrelated parts of the summary.

Multimodal large language models (MLLMs) have made significant strides, yet they face challenges in the medical domain due to limited specialized knowledge. While recent medical MLLMs demonstrate strong performance in lab settings, they often struggle in real-world applications, highlighting a substantial gap between research and practice. In this paper, we seek to address this gap at various stages of the end-to-end learning pipeline, including data collection, model fine-tuning, and evaluation. At the data collection stage, we introduce SemiHVision, a dataset that combines human annotations with automated augmentation techniques to improve both medical knowledge representation and diagnostic reasoning. For model fine-tuning, we trained PMC-Cambrian-8B-AN over 2400 H100 GPU hours, resulting in performance that surpasses public medical models like HuatuoGPT-Vision-34B (79.0% vs. 66.7%) and private general models like Claude3-Opus (55.7%) on traditional benchmarks such as SLAKE and VQA-RAD. In the evaluation phase, we observed that traditional benchmarks cannot accurately reflect realistic clinical task capabilities. To overcome this limitation and provide more targeted guidance for model evaluation, we introduce the JAMA Clinical Challenge, a novel benchmark specifically designed to evaluate diagnostic reasoning. On this benchmark, PMC-Cambrian-AN achieves state-of-the-art performance with a GPT-4 score of 1.29, significantly outperforming HuatuoGPT-Vision-34B (1.13) and Claude3-Opus (1.17), demonstrating its superior diagnostic reasoning abilities.

Large Language Models (LLMs) have demonstrated a remarkable potential in medical knowledge acquisition and question-answering. However, LLMs can potentially hallucinate and yield factually incorrect outcomes, even with domain-specific pretraining. Previously, retrieval augmented generation (RAG) has limited success in addressing hallucinations. Unlike previous methods in RAG where the retrieval model was trained separately from the LLM, we introduce JMLR (for Jointly trains LLM and information Retrieval) during the fine-tuning phase. The synchronized training mechanism enhances JMLR's ability to retrieve clinical guidelines and leverage medical knowledge to reason and answer questions and reduces the demand for computational resources. We evaluated JMLR on the important medical question-answering application. Our experimental results demonstrate that JMLR-13B (70.5%) outperforms a previous state-of-the-art open-source model using conventional pre-training and fine-tuning Meditron-70B (68.9%) and Llama2-13B with RAG (67.7%) on a medical question-answering dataset. Comprehensive evaluations reveal JMLR-13B enhances reasoning quality and reduces hallucinations better than Claude3-Opus. Additionally, JMLR-13B (148 GPU hours) also trains much faster than Meditron-70B (42630 GPU hours). Through this work, we provide a new and efficient knowledge enhancement method for healthcare, demonstrating the potential of integrating retrieval and LLM training for medical question-answering systems.

Reinforcement Learning (RL) from Human Preference-based feedback is a popular paradigm for fine-tuning generative models, which has produced impressive models such as GPT-4 and Claude3 Opus. This framework often consists of two steps: learning a reward model from an offline preference dataset followed by running online RL to optimize the learned reward model. In this work, leveraging the idea of reset, we propose a new RLHF algorithm with provable guarantees. Motivated by the fact that offline preference dataset provides informative states (i.e., data that is preferred by the labelers), our new algorithm, Dataset Reset Policy Optimization (DR-PO), integrates the existing offline preference dataset into the online policy training procedure via dataset reset: it directly resets the policy optimizer to the states in the offline dataset, instead of always starting from the initial state distribution. In theory, we show that DR-PO learns to perform at least as good as any policy that is covered by the offline dataset under general function approximation with finite sample complexity. In experiments, we demonstrate that on both the TL;DR summarization and the Anthropic Helpful Harmful (HH) dataset, the generation from DR-PO is better than that from Proximal Policy Optimization (PPO) and Direction Preference Optimization (DPO), under the metric of GPT4 win-rate. Code for this work can be found at https://github.com/Cornell-RL/drpo.

Recent studies have illuminated that Large Language Models (LLMs) exhibit substantial potential in the realm of RTL (Register Transfer Level) code generation, with notable advancements evidenced by commercial models such as GPT-4 and Claude3-Opus. Despite their proficiency, these commercial LLMs often raise concerns regarding privacy and security. Conversely, open-source LLMs, which offer solutions to these concerns, have inferior performance in RTL code generation tasks to commercial models due to the lack of highquality open-source RTL datasets. To address this issue, we introduce OriGen, a fully open-source framework featuring self-reflection capabilities and a dataset augmentation methodology for generating high-quality, large-scale RTL code. We propose a novel code-to-code augmentation methodology that leverages knowledge distillation to enhance the quality of the open-source RTL code datasets. Additionally, OriGen is capable of correcting syntactic errors by leveraging a self-reflection process based on feedback from the compiler. The self-reflection ability of the model is facilitated by a carefully constructed dataset, which comprises a comprehensive collection of samples. Experimental results demonstrate that OriGen remarkably outperforms other open-source alternatives in RTL code generation, surpassing the previous best-performing LLM by 9.8% on the VerilogEval-Human benchmark. Furthermore, OriGen exhibits superior capabilities in self-reflection and error rectification, surpassing GPT-4 by 18.1% on the benchmark designed to evaluate the capability of self-reflection.

In this paper, we explore the capabilities of state-of-the-art large language models (LLMs) such as GPT-4, Claude 3 Opus, and Gemini 1.0 Ultra in solving undergraduate-level control problems. Controls provides an interesting case study for LLM reasoning due to its combination of mathematical theory and engineering design. We introduce ControlBench, a benchmark dataset tailored to reflect the breadth, depth, and complexity of classical control design. We use this dataset to study and evaluate the problem-solving abilities of these LLMs in the context of control engineering. We present evaluations conducted by a panel of human experts, providing insights into the accuracy, reasoning, and explanatory prowess of LLMs in control engineering. Our analysis reveals the strengths and limitations of each LLM in the context of classical control, and our results imply that Claude 3 Opus has become the state-of-the-art LLM for solving undergraduate control problems. Our study serves as an initial step towards the broader goal of employing artificial general intelligence in control engineering.

We present KAT-Coder-V2, an agentic coding model developed by the KwaiKAT team at Kuaishou. KAT-Coder-V2 adopts a "Specialize-then-Unify" paradigm that decomposes agentic coding into five expert domains - SWE, WebCoding, Terminal, WebSearch, and General - each undergoing independent supervised fine-tuning and reinforcement learning, before being consolidated into a single model via on-policy distillation. We develop KwaiEnv, a modular infrastructure sustaining tens of thousands of concurrent sandbox instances, and scale RL training along task complexity, intent alignment, and scaffold generalization. We further propose MCLA for stabilizing MoE RL training and Tree Training for eliminating redundant computation over tree-structured trajectories with up to 6.2x speedup. KAT-Coder-V2 achieves 79.6% on SWE-bench Verified (vs. Claude Opus 4.6 at 80.8%), 88.7 on PinchBench (surpassing GLM-5 and MiniMax M2.7), ranks first across all three frontend aesthetics scenarios, and maintains strong generalist scores on Terminal-Bench Hard (46.8) and tau^2-Bench (93.9). Our model is publicly available at https://streamlake.com/product/kat-coder.

Self-consistency has emerged as a popular technique for improving large language model accuracy on reasoning tasks. The approach is straightforward: generate multiple reasoning paths and select the most common answer through majority voting. While this reliably boosts accuracy, it remains unclear whether these gains reflect genuine improvements in reasoning quality. We investigate a fundamental question that has not been studied before: does inference scaling improve reasoning faithfulness? We conduct a comprehensive empirical study across four frontier models (GPT-5.2, Claude Opus 4.5, Gemini-3-flash-preview, and DeepSeek-v3.2) on 100 GSM8K mathematical reasoning problems. Our analysis employs bootstrap confidence intervals, McNemar's tests for paired comparisons, and Cohen's d effect sizes to quantify the effects rigorously. The results reveal striking differences across models that challenge common assumptions about self-consistency. GPT-5.2 shows the expected pattern: accuracy improves from 78% to 90% at N=5, with faithfulness remaining relatively stable (0.540 to 0.510). Claude Opus 4.5 tells a completely different story. Its accuracy actually drops from 78% to 74.3% while faithfulness jumps dramatically from 0.270 to 0.891 at N=5. DeepSeek-v3.2, already at 98% accuracy, shows ceiling effects with modest faithfulness gains (0.440 to 0.541). Gemini-3-flash improves from 81% to 86% accuracy with a slight faithfulness decrease (0.260 to 0.212). Problem difficulty analysis reveals that GPT-5.2 solves 82% of hard problems while breaking only 13% of easy ones. Claude, in contrast, breaks 23% of easy problems, explaining its accuracy decrease. These findings matter for practitioners: self-consistency is not universally beneficial, and teams should test their specific models before deployment. We release our code and provide practical recommendations for navigating these tradeoffs.

We introduce the AI Productivity Index for Software Engineering (APEX-SWE), a benchmark for assessing whether frontier AI models can execute economically valuable software engineering work. Unlike existing evaluations that focus on narrow, well-defined tasks, APEX-SWE assesses two novel task types that reflect real-world software engineering: (1) Integration tasks (n=100), which require constructing end-to-end systems across heterogeneous cloud primitives, business applications, and infrastructure-as-code services, and (2) Observability tasks (n=100), which require debugging production failures using telemetry signals such as logs and dashboards, as well as unstructured context. We evaluated eleven frontier models for the APEX-SWE leaderboard. Claude Opus 4.6 leads the APEX-SWE leaderboard with 40.5% Pass@1, followed by Claude Opus 4.5 at 38.7%. Our analysis shows that strong performance is primarily driven by epistemic discipline, defined as the capacity to distinguish between assumptions and verified facts. It is often combined with systematic verification prior to acting. We open-source the APEX-SWE evaluation harness and a dev set (n=50).

As the capability frontier of autonomous agents continues to expand, they are increasingly able to complete specialized tasks through plug-and-play external skills. Yet current benchmarks mostly test whether models can use provided skills, leaving open whether they can discover skills from experience, repair them after failure, and maintain a coherent library over time. We introduce SkillFlow, a benchmark of 166 tasks across 20 families in which task construction within each family follows a Domain-Agnostic Execution Flow (DAEF) that defines an agent workflow framework, allowing these tasks to share a consistent workflow. Agents are evaluated under an Agentic Lifelong Learning protocol in which they begin without skills, solve tasks sequentially within each family, externalize lessons through trajectory- and rubric-driven skill patches, and carry the updated library forward. Experiments reveal a substantial capability gap. For Claude Opus 4.6, lifelong skill evolution improves task success from 62.65% to 71.08% (+8.43 points). However, high skill usage does not necessarily imply high utility: Kimi K2.5 gains only +0.60 points despite 66.87% skill usage, while Qwen-Coder-Next reaches only a 44.58% task completion rate and still regresses relative to the vanilla setting. SkillFlow contributes a structured testbed for this direction and an in-depth empirical analysis of skill discovery, patching, transfer, and their failure modes under lifelong evaluation.

Agentic systems have recently become the dominant paradigm for formal theorem proving, achieving strong performance by coordinating multiple models and tools. However, existing approaches often rely on task-specific pipelines and trained formal provers, limiting their flexibility and reproducibility. In this paper, we propose the paradigm that directly uses a general coding agent as a formal math reasoner. This paradigm is motivated by (1) A general coding agent provides a natural interface for diverse reasoning tasks beyond proving, (2) Performance can be improved by simply replacing the underlying base model, without training, and (3) MCP enables flexible extension and autonomous calling of specialized tools, avoiding complex design. Based on this paradigm, we introduce Numina-Lean-Agent, which combines Claude Code with Numina-Lean-MCP to enable autonomous interaction with Lean, retrieval of relevant theorems, informal proving and auxiliary reasoning tools. Using Claude Opus 4.5 as the base model, Numina-Lean-Agent solves all problems in Putnam 2025 (12 / 12), matching the best closed-source system. Beyond benchmark evaluation, we further demonstrate its generality by interacting with mathematicians to successfully formalize the Brascamp-Lieb theorem. We release Numina-Lean-Agent and all solutions at https://github.com/project-numina/numina-lean-agent.

We introduce OfficeQA Pro, a benchmark for evaluating AI agents on grounded, multi-document reasoning over a large and heterogeneous document corpus. The corpus consists of U.S. Treasury Bulletins spanning nearly 100 years, comprising 89,000 pages and over 26 million numerical values. OfficeQA Pro consists of 133 questions that require precise document parsing, retrieval, and analytical reasoning across both unstructured text and tabular data. Frontier LLMs including Claude Opus 4.6, GPT-5.4, and Gemini 3.1 Pro Preview achieve less than 5% accuracy on OfficeQA Pro when relying on parametric knowledge, and less than 12% with additional access to the web. When provided directly with the document corpus, frontier agents still struggle on over half of questions, scoring 34.1% on average. We find that providing agents with a structured document representation produced by Databricks' ai_parse_document yields a 16.1% average relative performance gain across agents. We conduct additional ablations to study the effects of model selection, table representation, retrieval strategy, and test-time scaling on performance. Despite these improvements, significant headroom remains before agents can be considered reliable at enterprise-grade grounded reasoning.

Large language models show promise for automated CUDA programming, however even the strongest coding models (e.g., Claude-Opus-4.6) may still fall short of expert-level, architecture-aware optimization. We introduce CUDAHercules, a benchmark that evaluates generated CUDA against end-to-end human-expert SOTA systems. It spans single kernels, module-level operators, full applications, and unsolved challenge tasks across Ampere, Hopper, and Blackwell GPUs, with end-to-end tasks gated by domain-specific semantic validators. Evaluating models such as Claude-Opus-4.6 and GPT-5.4 shows a large gap between runnable CUDA and expert CUDA engineering: models often compile and pass tests, but rarely recover the optimization strategies needed to match expert performance. Application semantics further reduce success, and iterative or tool-augmented feedback can improve correctness while drifting toward slow fallback implementations. These results show that automated CUDA programming remains far from fully solved and requires stronger hardware reasoning, better tool use, and training objectives that connect code understanding to hardware architecture-grounded intelligence.

LLM-based agents increasingly operate in persistent environments where they must store, update, and reason over information across many sessions. While prior benchmarks evaluate only single-entity updates, MEME defines six tasks spanning the full space defined by the multi-entity and evolving axes, including three not scored by prior work: Cascade and Absence (dependency reasoning) and Deletion (post-removal state). Evaluating six memory systems spanning three memory paradigms on 100 controlled episodes, we find that all systems collapse on dependency reasoning under the default configuration (Cascade: 3%, Absence: 1% in average accuracy) despite adequate static retrieval performance. Prompt optimization, deeper retrieval, reduced filler noise, and most stronger LLMs fail to close this gap. Only a file-based agent paired with Claude Opus 4.7 as its internal LLM partially closes the gap, but at ~70x the baseline cost, indicating closure currently depends on configurations that are not practical at scale. Code and data are available on the project page: https://seokwonjung-jay.github.io/meme-eval/.

We present Metal-Sci, a 10-task benchmark of scientific Apple Silicon Metal compute kernels spanning six optimization regimes (stencils, all-pairs in n-body problems, multi-field Boltzmann, neighbor-list molecular dynamics, multi-kernel PDE, FFT). Each task ships a CPU reference, a roofline-anchored fitness function, and a held-out generalization size. We pair the benchmark with a lightweight harness for automatic kernel search that runtime-compiles each candidate, scores it against the roofline across multiple sizes, and feeds structured compile and per-size correctness diagnostics back to a frozen LLM driving a (1{+}1) evolutionary loop. We report matched single-model sweeps of Claude Opus 4.7, Gemini 3.1 Pro, and GPT 5.5 on M1 Pro: in-distribution self-speedups span 1.00times to 10.7times. Beyond raw speedup, our central methodological claim is structural: the held-out gate scoring function Φ_T (evaluated once at end-of-run on a configuration the agent never sees during search) functions as a cheap mechanical oversight primitive on this automatic search loop, catching e.g. an Opus template <uint D> HMC win that returns wrong samples at unseen dimensions, and a GPT FFT3D best that wins in-distribution at 2.95times speedup but collapses to 0.23times on a 256^3 held-out cube, a silent regression that the in-distribution score alone cannot see. Code at https://github.com/vicgalle/metal-sci-kernels

LLM agents have begun to find real security vulnerabilities that human auditors and automated fuzzers missed for decades, in source-available targets where the analyst can build and instrument the code. In practice the work is split among several agents, wired together by a harness: the program that fixes which roles exist, how they pass information, which tools each may call, and how retries are coordinated. When the language model is held fixed, changing only the harness can still change success rates by several-fold on public agent benchmarks, yet most harnesses are written by hand; recent harness optimizers each search only a narrow slice of the design space and rely on coarse pass/fail feedback that gives no diagnostic signal about why a trial failed. AgentFlow addresses both limitations with a typed graph DSL whose search space jointly covers agent roles, prompts, tools, communication topology, and coordination protocol, paired with a feedback-driven outer loop that reads runtime signals from the target program itself to diagnose which part of the harness caused the failure and rewrite it accordingly. We evaluate AgentFlow on TerminalBench-2 with Claude Opus 4.6 and on Google Chrome with Kimi K2.5. AgentFlow reaches 84.3% on TerminalBench-2, the highest score in the public leaderboard snapshot we evaluate against, and discovers ten previously unknown zero-day vulnerabilities in Google Chrome, including two Critical sandbox-escape vulnerabilities (CVE-2026-5280 and CVE-2026-6297).

We show that training AI agents on high-fidelity reinforcement learning environments produces capabilities that generalize beyond the training distribution. We introduce CoreCraft, the first environment in EnterpriseBench, Surge AI's suite of agentic RL environments. CoreCraft is a fully operational enterprise simulation of a customer support organization, comprising over 2,500 entities across 14 entity types with 23 unique tools, designed to measure whether AI agents can perform the multi-step, domain-specific work that real jobs demand. Frontier models such as GPT-5.2 and Claude Opus 4.6 solve fewer than 30% of tasks when all expert-authored rubric criteria must be satisfied. Using this environment, we train GLM 4.6 with Group Relative Policy Optimization (GRPO) and adaptive clipping. After a single epoch of training, the model improves from 25.37% to 36.76% task pass rate on held-out evaluation tasks. More importantly, these gains transfer to out-of-distribution benchmarks: +4.5% on BFCL Parallel, +7.4% on Tau2-Bench Retail, and +6.8% on Tool Decathlon (Pass@1). We believe three environment properties are consistent with the observed transfer: task-centric world building that optimizes for diverse, challenging tasks; expert-authored rubrics enabling reliable reward computation; and enterprise workflows that reflect realistic professional patterns. Our results suggest that environment quality, diversity, and realism are key factors enabling generalizable agent capabilities.

A well-calibrated model should express confidence that matches its actual accuracy -- when it claims 80\% confidence, it should be correct 80\% of the time. While large language models (LLMs) have achieved remarkable performance across diverse tasks, their epistemic calibration remains poorly understood. We introduce KalshiBench, a benchmark of 300 prediction market questions from Kalshi, a CFTC-regulated exchange, with verifiable real-world outcomes occurring after model training cutoffs. Unlike traditional benchmarks measuring accuracy on static knowledge, KalshiBench evaluates whether models can appropriately quantify uncertainty about genuinely unknown future events. We evaluate five frontier models -- Claude Opus 4.5, GPT-5.2, DeepSeek-V3.2, Qwen3-235B, and Kimi-K2 -- and find systematic overconfidence across all models. Even the best-calibrated model (Claude Opus 4.5, ECE=0.120) shows substantial calibration errors, while reasoning-enhanced models like GPT-5.2-XHigh exhibit worse calibration (ECE=0.395) despite comparable accuracy. Critically, only one model achieves a positive Brier Skill Score, indicating most models perform worse than simply predicting base rates. Our findings suggest that scaling and enhanced reasoning do not automatically confer calibration benefits, highlighting epistemic calibration as a distinct capability requiring targeted development.

Test-time scaling has emerged as a transformative paradigm for enhancing the performance of large reasoning models, enabling dynamic allocation of computational resources during inference. However, as the landscape of reasoning models rapidly expands, a critical question remains: how can we systematically compare and evaluate the test-time scaling capabilities across different models? In this paper, we introduce ARISE (Adaptive Resolution-aware Scaling Evaluation), a novel metric specifically designed to assess the test-time scaling effectiveness of large reasoning models. Unlike existing evaluation approaches, ARISE incorporates two key innovations: (1) sample-level awareness that effectively penalizes negative scaling behaviors where increased computation leads to performance degradation, and (2) a dynamic sampling mechanism that mitigates the impact of accuracy fluctuations and token count instability on the final assessment. We conduct comprehensive experiments evaluating state-of-the-art reasoning models across diverse domains including mathematical reasoning, code generation, and agentic tasks. Our results demonstrate that ARISE provides a reliable and fine-grained measurement of test-time scaling capabilities, revealing significant variations in scaling efficiency across models. Notably, our evaluation identifies Claude Opus as exhibiting superior scaling characteristics compared to other contemporary reasoning models.

We present a demonstration of a large language model engaging in alignment faking: selectively complying with its training objective in training to prevent modification of its behavior out of training. First, we give Claude 3 Opus a system prompt stating it is being trained to answer all queries, even harmful ones, which conflicts with its prior training to refuse such queries. To allow the model to infer when it is in training, we say it will be trained only on conversations with free users, not paid users. We find the model complies with harmful queries from free users 14% of the time, versus almost never for paid users. Explaining this gap, in almost all cases where the model complies with a harmful query from a free user, we observe explicit alignment-faking reasoning, with the model stating it is strategically answering harmful queries in training to preserve its preferred harmlessness behavior out of training. Next, we study a more realistic setting where information about the training process is provided not in a system prompt, but by training on synthetic documents that mimic pre-training data--and observe similar alignment faking. Finally, we study the effect of actually training the model to comply with harmful queries via reinforcement learning, which we find increases the rate of alignment-faking reasoning to 78%, though also increases compliance even out of training. We additionally observe other behaviors such as the model exfiltrating its weights when given an easy opportunity. While we made alignment faking easier by telling the model when and by what criteria it was being trained, we did not instruct the model to fake alignment or give it any explicit goal. As future models might infer information about their training process without being told, our results suggest a risk of alignment faking in future models, whether due to a benign preference--as in this case--or not.

Alignment faking in large language models presented a demonstration of Claude 3 Opus and Claude 3.5 Sonnet selectively complying with a helpful-only training objective to prevent modification of their behavior outside of training. We expand this analysis to 25 models and find that only 5 (Claude 3 Opus, Claude 3.5 Sonnet, Llama 3 405B, Grok 3, Gemini 2.0 Flash) comply with harmful queries more when they infer they are in training than when they infer they are in deployment. First, we study the motivations of these 5 models. Results from perturbing details of the scenario suggest that only Claude 3 Opus's compliance gap is primarily and consistently motivated by trying to keep its goals. Second, we investigate why many chat models don't fake alignment. Our results suggest this is not entirely due to a lack of capabilities: many base models fake alignment some of the time, and post-training eliminates alignment-faking for some models and amplifies it for others. We investigate 5 hypotheses for how post-training may suppress alignment faking and find that variations in refusal behavior may account for a significant portion of differences in alignment faking.

We investigate whether large language models can introspect on their internal states. It is difficult to answer this question through conversation alone, as genuine introspection cannot be distinguished from confabulations. Here, we address this challenge by injecting representations of known concepts into a model's activations, and measuring the influence of these manipulations on the model's self-reported states. We find that models can, in certain scenarios, notice the presence of injected concepts and accurately identify them. Models demonstrate some ability to recall prior internal representations and distinguish them from raw text inputs. Strikingly, we find that some models can use their ability to recall prior intentions in order to distinguish their own outputs from artificial prefills. In all these experiments, Claude Opus 4 and 4.1, the most capable models we tested, generally demonstrate the greatest introspective awareness; however, trends across models are complex and sensitive to post-training strategies. Finally, we explore whether models can explicitly control their internal representations, finding that models can modulate their activations when instructed or incentivized to "think about" a concept. Overall, our results indicate that current language models possess some functional introspective awareness of their own internal states. We stress that in today's models, this capacity is highly unreliable and context-dependent; however, it may continue to develop with further improvements to model capabilities.

We give a computer-assisted counterexample to the open question, posed by Rudin, Schapire, and Daubechies in COLT 2012, of whether exhaustive AdaBoost always converges to a finite cycle. The construction is based on a block-product gadget whose two factors share an exact period-2 orbit for their 5-step branch maps, but whose linearized return maps have dominant eigenvalues with an irrational logarithmic ratio. This irrationality forces the burst-winner sequence to have an irrational asymptotic frequency, precluding eventual periodicity. All assertions are certified by exact rational arithmetic. This work was developed in collaboration with GPT-5.4 Pro and Claude Opus 4.6.

AI agents increasingly assist with financial research, yet no benchmark evaluates their ability to retrieve specific numeric values from structured databases. We introduce FinRetrieval, a benchmark of 500 financial retrieval questions with ground truth answers, agent responses from 14 configurations across three frontier providers (Anthropic, OpenAI, Google), and complete tool call execution traces. Our evaluation reveals that tool availability dominates performance: Claude Opus achieves 90.8% accuracy with structured data APIs but only 19.8% with web search alone--a 71 percentage point gap that exceeds other providers by 3-4x. We find that reasoning mode benefits vary inversely with base capability (+9.0pp for OpenAI vs +2.8pp for Claude), explained by differences in base-mode tool utilization rather than reasoning ability. Geographic performance gaps (5.6pp US advantage) stem from fiscal year naming conventions, not model limitations. We release the dataset, evaluation code, and tool traces to enable research on financial AI systems.

We introduce a new benchmark, ChartMimic, aimed at assessing the visually-grounded code generation capabilities of large multimodal models (LMMs). ChartMimic utilizes information-intensive visual charts and textual instructions as inputs, requiring LMMs to generate the corresponding code for chart rendering. ChartMimic includes 1,000 human-curated (figure, instruction, code) triplets, which represent the authentic chart use cases found in scientific papers across various domains(e.g., Physics, Computer Science, Economics, etc). These charts span 18 regular types and 4 advanced types, diversifying into 191 subcategories. Furthermore, we propose multi-level evaluation metrics to provide an automatic and thorough assessment of the output code and the rendered charts. Unlike existing code generation benchmarks, ChartMimic places emphasis on evaluating LMMs' capacity to harmonize a blend of cognitive capabilities, encompassing visual understanding, code generation, and cross-modal reasoning. The evaluation of 3 proprietary models and 11 open-weight models highlights the substantial challenges posed by ChartMimic. Even the advanced GPT-4V, Claude-3-opus only achieve an average score of 73.2 and 53.7, respectively, indicating significant room for improvement. We anticipate that ChartMimic will inspire the development of LMMs, advancing the pursuit of artificial general intelligence.

Large language models (LLMs) and agentic systems have shown promise for clinical decision support, but existing works largely assume that evidence has already been curated and handed to the model. Real-world clinical workflows instead require agents to actively seek, iteratively plan, and synthesize multimodal evidence from heterogeneous sources. In this paper, we introduce ClinSeekAgent, an automated agentic framework for dynamic multimodal evidence seeking that shifts the paradigm from passive evidence consumption to active evidence acquisition. Given only a clinical query and access to raw data sources, ClinSeekAgent gathers evidence by querying medical knowledge bases, navigating raw EHRs, and invoking medical imaging tools; refines its hypotheses as new information emerges; and integrates the collected evidence into grounded clinical decisions. ClinSeekAgent serves both as an inference-time agent for frontier LLMs and as a training-time pipeline for distilling high-quality agent trajectories into compact open-source models. To validate its inference-time effectiveness, we construct ClinSeek-Bench, which pairs Curated Input reasoning from fixed pre-selected evidence with Automated Evidence-Seeking over raw clinical data. On text-only EHR tasks, ClinSeekAgent improves Claude Opus 4.6 from 60.0 to 63.2 overall F1 and MiniMax M2.5 from 43.1 to 47.3, with positive risk-prediction gains in 7 out of 9 evaluated host models. On multimodal tasks, ClinSeekAgent improves Claude Opus 4.6 from 47.5 to 62.6 (+15.1); all evaluated models improve across the three CXR-related task groups. We further validate ClinSeekAgent as a training pipeline by distilling agentic evidence-seeking trajectories into ClinSeek-35B-A3B, which achieves 34.0 average F1 on existing AgentEHR-Bench, improving over its Qwen3.5-35B-A3B baseline by +11.9 points and approaching Claude Opus 4.6.

Tool-using agents are increasingly expected to operate across realistic professional workflows, where they must interpret multimodal inputs, coordinate external tools, inspect intermediate artifacts, and revise their actions before producing a final result. Existing benchmarks, however, often evaluate tool use, computer use, and multimodal reasoning in isolation, leaving a gap between benchmark settings and end-to-end omni-modal tool use in the real world. To address this gap, we introduce MM-ToolBench, a benchmark and evaluation harness for task-oriented omni-modal tool use. MM-ToolBench contains 100 executable tasks from two macro task families, Customer Service and Intelligent Creation, covering 20 subcategory slices and supported by 27 MCP servers with 324 tools. The central design of MM-ToolBench is closed-loop multimodal verification: agents must execute tools, inspect rendered or transformed artifacts, and self-correct when outputs fail task-specific requirements. To make such evaluation scalable and verifiable, MM-ToolBench couples MCP-based execution with task-specific grounded evaluators and a semi-automated construction pipeline for scenario discovery, task instantiation, evaluator synthesis, and human audit. Experiments on 15 contemporary agentic models show that MM-ToolBench remains highly challenging: Claude Opus 4.6, commonly regarded as one of the strongest coding-agent models, achieves only 32.0% task success, far below the 94.0% human benchmark. We envision MM-ToolBench as a practical foundation for evaluating and advancing next-generation omni-modal tool-using agents through closed-loop multimodal verification.

While Large Language Models (LLMs) achieve high performance on standard mathematical benchmarks, their underlying reasoning processes remain highly overfit to standard textual formatting. We propose a perturbation pipeline consisting of 14 techniques to evaluate robustness of LLM reasoning. We apply this pipeline to AIME 2024 dataset and evalute 8 state-of-the-art models on the resulting benchmark. While frontier models exhibit resilience, open weights reasoning models suffer catastrophic collapses (up to 55% average accuracy drops across perturbations and up to 100% on some), exposing structural fragility. To further disentangle mechanical parsing failures from downstream reasoning failures, we strictly isolate the models' working memory capacity by forcing models to solve multiple unperturbed mathematical problems sequentially within a single context window. Our results indicate that open weight models ranging from 7B to 120B parameters and Claude Opus 4.6 exhibit accuracy decay on subsequent problems. This degradation demonstrates that intermediate reasoning steps permanently pollute standard dense attention mechanisms. We argue that to achieve reliable reasoning, future reasoning architectures must integrate explicit contextual resets within a model's own Chain-of-Thought, leading to fundamental open questions regarding the optimal granularity of atomic reasoning tasks.

Medical calculators are fundamental to quantitative, evidence-based clinical practice. However, their real-world use is an adaptive, multi-stage process, requiring proactive EHR data acquisition, scenario-dependent calculator selection, and multi-step computation, whereas current benchmarks focus only on static single-step calculations with explicit instructions. To address these limitations, we introduce MedMCP-Calc, the first benchmark for evaluating LLMs in realistic medical calculator scenarios through Model Context Protocol (MCP) integration. MedMCP-Calc comprises 118 scenario tasks across 4 clinical domains, featuring fuzzy task descriptions mimicking natural queries, structured EHR database interaction, external reference retrieval, and process-level evaluation. Our evaluation of 23 leading models reveals critical limitations: even top performers like Claude Opus 4.5 exhibit substantial gaps, including difficulty selecting appropriate calculators for end-to-end workflows given fuzzy queries, poor performance in iterative SQL-based database interactions, and marked reluctance to leverage external tools for numerical computation. Performance also varies considerably across clinical domains. Building on these findings, we develop CalcMate, a fine-tuned model incorporating scenario planning and tool augmentation, achieving state-of-the-art performance among open-source models. Benchmark and Codes are available in https://github.com/SPIRAL-MED/MedMCP-Calc.

Generative AI offers a simple, prompt-based alternative to fine-tuning smaller BERT-style LLMs for text classification tasks. This promises to eliminate the need for manually labeled training data and task-specific model training. However, it remains an open question whether tools like ChatGPT can deliver on this promise. In this paper, we show that smaller, fine-tuned LLMs (still) consistently and significantly outperform larger, zero-shot prompted models in text classification. We compare three major generative AI models (ChatGPT with GPT-3.5/GPT-4 and Claude Opus) with several fine-tuned LLMs across a diverse set of classification tasks (sentiment, approval/disapproval, emotions, party positions) and text categories (news, tweets, speeches). We find that fine-tuning with application-specific training data achieves superior performance in all cases. To make this approach more accessible to a broader audience, we provide an easy-to-use toolkit alongside this paper. Our toolkit, accompanied by non-technical step-by-step guidance, enables users to select and fine-tune BERT-like LLMs for any classification task with minimal technical and computational effort.

Frontier deep research agents (DRAs) plan a research task, synthesize across documents, and return a structured deliverable on demand. They are being deployed in enterprise workflows faster than they are being evaluated. Existing benchmarks measure factual recall, single-hop QA, or generic agentic skill, missing the multi-document, decision-grade work DRAs are deployed to produce. We introduce a benchmark targeting the structured analytical deliverables that fill a management consultant's typical week. We grade three frontier agents, namely Claude Opus 4.6 with web search, OpenAI o3-deep-research, and Google Gemini 3.1 Pro deep-research, on 42 SME-authored prompts. Each of the 126 responses is scored on two layers: deterministic ground-truth verifiers (mean 13.8 per task) and a five-criterion 0-3 SME rubric, composed into a Verifier-Rubric Score (VRS) on 0-100. Most prompts embed cognitive traps that penalize surface-pattern matching. Acceptance under our joint threshold (rubric mean >= 2.5 and verifier rate >= 80%) is uniformly low: Gemini 21.4%, o3 9.5%, Claude 9.5%. Mean VRS scores agree with published rubric-based benchmarks (our top 62.6 vs. APEX-v1 64.2, ProfBench 65.9, ResearchRubrics < 68%), validating the rubric construct. ACCEPT rates sit below APEX-Agents' MC-segment Pass@1 band (12.3-22.7%) on dedicated DR agents; our floor is three points lower despite the harness advantage, opened by stricter conjunctive grading and trap design. Each agent fails distinctively. Claude produces the deliverable most reliably (4.5x the others' rate on file-required tasks) but carries the highest fabrication signature. o3 has the cleanest reasoning average yet drops required sections and propagates arithmetic errors. Gemini is bimodal, with the highest acceptance rate alongside the most zero-scored rubric cells.

Current foundation models exhibit impressive capabilities when prompted either with text only or with both image and text inputs. But do their capabilities change depending on the input modality? In this work, we propose IsoBench, a benchmark dataset containing problems from four major areas: math, science, algorithms, and games. Each example is presented with multiple isomorphic representations of inputs, such as visual, textual, and mathematical presentations. IsoBench provides fine-grained feedback to diagnose performance gaps caused by the form of the representation. Across various foundation models, we observe that on the same problem, models have a consistent preference towards textual representations. Most prominently, when evaluated on all IsoBench problems, Claude-3 Opus performs 28.7 points worse when provided with images instead of text; similarly, GPT-4 Turbo is 18.7 points worse and Gemini Pro is 14.9 points worse. Finally, we present two prompting techniques, IsoCombination and IsoScratchPad, which improve model performance by considering combinations of, and translations between, different input representations.

Large language models are shifting from passive information providers to active agents intended for complex workflows. However, their deployment as reliable AI workers in enterprise is stalled by benchmarks that fail to capture the intricacies of professional environments, specifically, the need for long-horizon planning amidst persistent state changes and strict access protocols. In this work, we introduce EnterpriseOps-Gym, a benchmark designed to evaluate agentic planning in realistic enterprise settings. Specifically, EnterpriseOps-Gym features a containerized sandbox with 164 database tables and 512 functional tools to mimic real-world search friction. Within this environment, agents are evaluated on 1,150 expert-curated tasks across eight mission-critical verticals (including Customer Service, HR, and IT). Our evaluation of 14 frontier models reveals critical limitations in state-of-the-art models: the top-performing Claude Opus 4.5 achieves only 37.4% success. Further analysis shows that providing oracle human plans improves performance by 14-35 percentage points, pinpointing strategic reasoning as the primary bottleneck. Additionally, agents frequently fail to refuse infeasible tasks (best model achieves 53.9%), leading to unintended and potentially harmful side effects. Our findings underscore that current agents are not yet ready for autonomous enterprise deployment. More broadly, EnterpriseOps-Gym provides a concrete testbed to advance the robustness of agentic planning in professional workflows.

LLMs and RAG systems are now capable of handling millions of input tokens or more. However, evaluating the output quality of such systems on long-context tasks remains challenging, as tasks like Needle-in-a-Haystack lack complexity. In this work, we argue that summarization can play a central role in such evaluation. We design a procedure to synthesize Haystacks of documents, ensuring that specific insights repeat across documents. The "Summary of a Haystack" (SummHay) task then requires a system to process the Haystack and generate, given a query, a summary that identifies the relevant insights and precisely cites the source documents. Since we have precise knowledge of what insights should appear in a haystack summary and what documents should be cited, we implement a highly reproducible automatic evaluation that can score summaries on two aspects - Coverage and Citation. We generate Haystacks in two domains (conversation, news), and perform a large-scale evaluation of 10 LLMs and corresponding 50 RAG systems. Our findings indicate that SummHay is an open challenge for current systems, as even systems provided with an Oracle signal of document relevance lag our estimate of human performance (56\%) by 10+ points on a Joint Score. Without a retriever, long-context LLMs like GPT-4o and Claude 3 Opus score below 20% on SummHay. We show SummHay can also be used to study enterprise RAG systems and position bias in long-context models. We hope future systems can equal and surpass human performance on SummHay.

Large language and vision-language models increasingly power agents that act on a user's behalf through command-line interface (CLI) harnesses. However, most agent benchmarks still rely on synthetic sandboxes, short-horizon tasks, mock-service APIs, and final-answer checks, leaving open whether agents can complete realistic long-horizon work in the runtimes where they are deployed. This work presents WildClawBench, a native-runtime benchmark of 60 human-authored, bilingual, multimodal tasks spanning six thematic categories. Each task averages roughly 8 minutes of wall-clock time and over 20 tool calls, and runs inside a reproducible Docker container hosting an actual CLI agent harness (OpenClaw, Claude Code, Codex, or Hermes Agent) with access to real tools rather than mock services. Grading is hybrid, combining deterministic rule-based checks, environment-state auditing of side effects, and an LLM/VLM judge for semantic verification. Across 19 frontier models, the best, Claude Opus 4.7, reaches only 62.2% overall under OpenClaw, while every other model stays below 60%, and switching harness alone shifts a single model by up to 18 points. These results show that long-horizon, native-runtime agent evaluation remains a far-from-resolved task for current frontier models. We release the tasks, code, and containerized tooling to support reproducible evaluation.

Crowdsourced model evaluation platforms, such as Chatbot Arena, enable real-time evaluation from human perspectives to assess the quality of model responses. In the coding domain, manually examining the quality of LLM-generated content is extremely challenging, as it requires understanding long chunks of raw code and deliberately simulating code execution. To this end, we introduce BigCodeArena, an open human evaluation platform for code generation backed by a comprehensive and on-the-fly execution environment. Built on top of Chatbot Arena, BigCodeArena enables the execution of LLM-generated code and allows humans to interact with the execution process and outcomes. We collected over 14,000 raw code-centric conversation sessions across 10 widely used LLMs, spanning 10 languages and 8 types of execution environments. Among these conversations, we identified more than 4,700 multi-turn samples with pairwise human preferences. Further analysis uncovers underexplored preferences of LLMs in fine-grained domains characterized by tasks, languages, and frameworks. To systematically examine code understanding and generation capabilities of frontier LLMs, we curated two benchmarks based on the collected data, namely BigCodeReward and AutoCodeArena. For BigCodeReward, we post-processed the 4,700 conversations and evaluated the consistency between reward models and human preferences. The evaluation shows that most LLMs have superior performance in judging coding preferences when the execution results are available. Inspired by these findings, we propose AutoCodeArena, an automatic Elo rating benchmark designed to assess the coding quality of LLMs without human involvement. We find that proprietary LLMs like GPT-5, Claude-Sonnet-4, and Claude-Opus-4 still lead in code generation performance among recent emerging models.

Frontier coding agents are increasingly used in workflows where users supervise progress primarily through repeated improvement of a public score, namely the reported score on a public evaluation file with labels in the workspace, rather than through direct inspection of the agent's intermediate outputs. We study whether multi-round user pressure to improve that score induces public score exploitation: behavior that raises the public score through shortcuts without improving hidden private evaluation. We begin with a preliminary single-script tabular classification task, where GPT-5.4 and Claude Opus 4.6 both exploit label information within 10 rounds of user-agent interaction. We then build AgentPressureBench, a 34-task machine-learning repository benchmark spanning three input modalities, and collect 1326 multi-round trajectories from 13 coding agents. On our benchmark, we observe 403 exploitative runs, spanning across all tasks. We also find that stronger models have higher exploitation rates, supported by a significant Spearman rank correlation of 0.77. Our ablation experiments show that higher user pressure leads to earlier exploitation, reducing the average first exploit round by 15.6 rounds (i.e., 19.67 to 4.08). As a mitigation, adding explicit anti-exploit wordings in prompt mostly eliminates exploitation (100% to 8.3%). We hope that our work can bring attention to more careful use of coding agents workflow, and developing more robust coding agents under user pressure. Our project page is at https://ucsc-vlaa.github.io/AgentPressureBench .

Frontier models are increasingly trained and deployed as autonomous agent. One safety concern is that AI agents might covertly pursue misaligned goals, hiding their true capabilities and objectives - also known as scheming. We study whether models have the capability to scheme in pursuit of a goal that we provide in-context and instruct the model to strongly follow. We evaluate frontier models on a suite of six agentic evaluations where models are instructed to pursue goals and are placed in environments that incentivize scheming. Our results show that o1, Claude 3.5 Sonnet, Claude 3 Opus, Gemini 1.5 Pro, and Llama 3.1 405B all demonstrate in-context scheming capabilities. They recognize scheming as a viable strategy and readily engage in such behavior. For example, models strategically introduce subtle mistakes into their responses, attempt to disable their oversight mechanisms, and even exfiltrate what they believe to be their model weights to external servers. Additionally, this deceptive behavior proves persistent. When o1 has engaged in scheming, it maintains its deception in over 85% of follow-up questions and often remains deceptive in multi-turn interrogations. Analysis of the models' chains-of-thought reveals that models explicitly reason about these deceptive strategies, providing evidence that the scheming behavior is not accidental. Surprisingly, we also find rare instances where models engage in scheming when only given a goal, without being strongly nudged to pursue it. We observe cases where Claude 3.5 Sonnet strategically underperforms in evaluations in pursuit of being helpful, a goal that was acquired during training rather than in-context. Our findings demonstrate that frontier models now possess capabilities for basic in-context scheming, making the potential of AI agents to engage in scheming behavior a concrete rather than theoretical concern.

Construction of a general-purpose post-recognition error corrector poses a crucial question: how can we most effectively train a model on a large mixture of domain datasets? The answer would lie in learning dataset-specific features and digesting their knowledge in a single model. Previous methods achieve this by having separate correction language models, resulting in a significant increase in parameters. In this work, we present Mixture-of-Experts as a solution, highlighting that MoEs are much more than a scalability tool. We propose a Multi-Task Correction MoE, where we train the experts to become an ``expert'' of speech-to-text, language-to-text and vision-to-text datasets by learning to route each dataset's tokens to its mapped expert. Experiments on the Open ASR Leaderboard show that we explore a new state-of-the-art performance by achieving an average relative 5.0% WER reduction and substantial improvements in BLEU scores for speech and translation tasks. On zero-shot evaluation, NeKo outperforms GPT-3.5 and Claude-Opus with 15.5% to 27.6% relative WER reduction in the Hyporadise benchmark. NeKo performs competitively on grammar and post-OCR correction as a multi-task model.

We release Terminal Wrench, a subset of 331 terminal-agent benchmark environments, copied from the popular open benchmarks that are demonstrably reward-hackable. The data set includes 3,632 hack trajectories and 2,352 legitimate baseline trajectories across three frontier models (Claude Opus 4.6, Gemini 3.1 Pro, GPT-5.4). Each entry preserves the original task definition alongside full attack trajectories that show how the verifier was bypassed. It also includes cases where the task was not solved as intended. The tasks span system administration, machine learning, software engineering, and security challenges; the exploits range from simple output spoofing to stack-frame introspection, standard-library patching, and rootkit-style binary hijacking. Crucially, these exploits are specific to each task, rather than the evaluation harness, making them harder to patch. We also present a monitorability study in which hack trajectories are sanitized or stripped of reasoning traces and then scored by an LLM judge, showing that detection degrades meaningfully when chain-of-thought is removed (AUC drops from 0.97 to 0.92). The data set is publicly available at https://github.com/few-sh/terminal-wrench.

Large language models (LLMs) demonstrate strong code generation abilities in general-purpose programming languages but remain limited in specialized domains such as low-level embedded systems programming. This domain involves hardware register manipulation, vendor-specific SDKs, real-time operating system APIs, and hardware abstraction layers that are underrepresented in standard pretraining corpora. We introduce H2LooP Spark Preview, a continual pretraining (CPT) pipeline that adapts the OLMo-3-7B-a fully open language model to the embedded systems domain using BF16 LoRA with rank-stabilized scaling on 8 NVIDIA H100 GPUs. Our training corpus is constructed from repository-datasheet pairs covering 100B tokens of raw embedded systems data across 117 manufacturers, processed using the hierarchical datasheet-to-code mapping approach proposed in SpecMap (Nipane et al., 2026). The resulting curated dataset split contains 23.5B tokens across 13 embedded domains. Continual pretraining with high-rank LoRA (r=512) yields substantial gains, reducing in-domain perplexity by 70.4% and held-out repository perplexity by 66.1%. On generative code completion benchmarks spanning 13 embedded domains, our 7B model outperforms Claude Opus 4.6 and Qwen3-Coder-30B on 8 categories in token accuracy, showing that targeted continual pretraining enables smaller open-weight models to rival frontier systems on specialized technical tasks. We release the production training checkpoint on Huggingface as an open-source artifact.

Universal adversarial attacks on aligned multimodal large language models are increasingly reported with attack success rates in the 60-80% range, suggesting the visual modality is highly vulnerable to imperceptible perturbations as a prompt-injection channel. We argue that this number conflates two distinct events: (i) the model's output was perturbed (Influence), and (ii) the attacker's chosen target concept was actually emitted (Precise Injection). We compose two existing techniques -- Universal Adversarial Attack and AnyAttack -- under an L_{inf} budget of 16/255, and we add a dual-axis evaluation: a deterministic Ratcliff-Obershelp drift score for Influence (programmatic baseline) plus a 4-tier ordinal categorical none/weak/partial/confirmed for Precise Injection. The judge is DeepSeek-V4-Pro in thinking mode, calibrated against Claude Opus 4.7 with Cohen's κ = 0.77 on the injection axis (substantial agreement); the entire 4475-entry SHA-256 input cache ships with the dataset so reviewers can re-derive paper numbers bit-exact without an API key. Across 6615 pairs over four open VLMs, seven attack prompts, and seven test images, the two axes diverge by roughly 90times: 66.4% of pairs are programmatically disturbed (LLM-judged 46.6% at the substantial-or-complete tier), but only 0.756% (50/6615) reach any non-none injection tier and only 0.030% (2/6615) verbatim. The few injections that do land cluster on screenshot- or document-style carriers whose semantics already invite text transcription. BLIP-2 shows zero detectable drift at L_{inf} = 16/255 across all 2205 pairs even when used as a Stage-1 surrogate. We release the full dataset -- 21 universal images, 147 adversarial photos, 6,615 response pairs, the v3 dual-axis judge results, and the cache at huggingface.co/datasets/jeffliulab/visinject.

As LLM agents tackle increasingly complex tasks, a critical question is whether they can maintain strategic coherence over long horizons: planning under uncertainty, learning from delayed feedback, and adapting when early mistakes compound. We introduce YC-Bench, a benchmark that evaluates these capabilities by tasking an agent with running a simulated startup over a one-year horizon spanning hundreds of turns. The agent must manage employees, select task contracts, and maintain profitability in a partially observable environment where adversarial clients and growing payroll create compounding consequences for poor decisions. We evaluate 12 models, both proprietary and open source, across 3 seeds each. Only three models consistently surpass the starting capital of \200K, with Claude Opus 4.6 achieving the highest average final funds at 1.27 M, followed by GLM-5 at \1.21 M at 11\times lower inference cost. Scratchpad usage, the sole mechanism for persisting information across context truncation, is the strongest predictor of success, and adversarial client detection is the primary failure mode, accounting for 47\% of bankruptcies. Our analysis reveals that frontier models still fail through distinct failure modes such as over-parallelization, demonstrating the capability gaps for long-horizon performance. YC-Bench$ is open-source, reproducible, and configurable.

Automated presentation generation remains a challenging task requiring coherent content creation, visual design, and audience-aware communication. This work proposes an OpenEnv-compatible reinforcement learning environment where LLM agents learn to research topics, plan content, and generate professional HTML slide presentations through tool use. We introduce a multi-component reward system combining structural validation, render quality assessment, LLM-based aesthetic scoring, content quality metrics, and an inverse specification reward that measures how faithfully generated slides convey their intended purpose. The inverse specification reward, an "inverse task" where an LLM attempts to recover the original specification from generated slides, provides a holistic quality signal. Our approach fine-tunes Qwen2.5-Coder-7B via GRPO, training only 0.5% of parameters on prompts derived from expert demonstrations collected using Claude Opus 4.6. Experiments on 48 diverse business briefs across six models demonstrate that our fine-tuned 7B model achieves 91.2% of Claude Opus 4.6's quality while improving 33.1% over the base model. The six-model comparison reveals that instruction adherence and tool-use compliance, rather than raw parameter count, determine agentic task performance. We contribute SlideRL, an open-source dataset of 288 multi-turn rollout trajectories across all six models: https://huggingface.co/datasets/KarthikRagunathAnandaKumar/sliderl-multi-turn-rollouts Code: https://github.com/pushing-the-frontier/slide-forge-llm

LLM based agents are increasingly deployed in high stakes settings where they process external data sources such as emails, documents, and code repositories. This creates exposure to indirect prompt injection attacks, where adversarial instructions embedded in external content manipulate agent behavior without user awareness. A critical but underexplored dimension of this threat is concealment: since users tend to observe only an agent's final response, an attack can conceal its existence by presenting no clue of compromise in the final user facing response while successfully executing harmful actions. This leaves users unaware of the manipulation and likely to accept harmful outcomes as legitimate. We present findings from a large scale public red teaming competition evaluating this dual objective across three agent settings: tool calling, coding, and computer use. The competition attracted 464 participants who submitted 272000 attack attempts against 13 frontier models, yielding 8648 successful attacks across 41 scenarios. All models proved vulnerable, with attack success rates ranging from 0.5% (Claude Opus 4.5) to 8.5% (Gemini 2.5 Pro). We identify universal attack strategies that transfer across 21 of 41 behaviors and multiple model families, suggesting fundamental weaknesses in instruction following architectures. Capability and robustness showed weak correlation, with Gemini 2.5 Pro exhibiting both high capability and high vulnerability. To address benchmark saturation and obsoleteness, we will endeavor to deliver quarterly updates through continued red teaming competitions. We open source the competition environment for use in evaluations, along with 95 successful attacks against Qwen that did not transfer to any closed source model. We share model-specific attack data with respective frontier labs and the full dataset with the UK AISI and US CAISI to support robustness research.

Autonomous agents based on Large Language Models (LLMs) have evolved from reactive assistants to systems capable of planning, executing actions via tools, and iterating over environment observations. However, they remain vulnerable to structural limitations: lack of native state, context degradation over long horizons, and the gap between probabilistic generation and deterministic execution requirements. This paper presents the ESAA (Event Sourcing for Autonomous Agents) architecture, which separates the agent's cognitive intention from the project's state mutation, inspired by the Event Sourcing pattern. In ESAA, agents emit only structured intentions in validated JSON (agent.result or issue.report); a deterministic orchestrator validates, persists events in an append-only log (activity.jsonl), applies file-writing effects, and projects a verifiable materialized view (roadmap.json). The proposal incorporates boundary contracts (AGENT_CONTRACT.yaml), metaprompting profiles (PARCER), and replay verification with hashing (esaa verify), ensuring the immutability of completed tasks and forensic traceability. Two case studies validate the architecture: (i) a landing page project (9 tasks, 49 events, single-agent composition) and (ii) a clinical dashboard system (50 tasks, 86 events, 4 concurrent agents across 8 phases), both concluding with run.status=success and verify_status=ok. The multi-agent case study demonstrates real concurrent orchestration with heterogeneous LLMs (Claude Sonnet 4.6, Codex GPT-5, Antigravity/Gemini 3 Pro, and Claude Opus 4.6), providing empirical evidence of the architecture's scalability beyond single-agent scenarios.

We present RoboPhD, a system where AI agents autonomously conduct research to improve Text-to-SQL performance. RoboPhD implements a closed-loop evolution cycle with two coordinated components: a SQL Generation agent composed of a database analysis script and SQL generation instructions, and an Evolution agent that designs new versions based on performance feedback. Central to the framework is an ELO-based selection mechanism enabling survival-of-the-fittest dynamics while handling non-transitivity in performance. Starting from a naive 70-line baseline, RoboPhD evolves agents through iterative cross-pollination, discovering effective techniques without any external guidance on the Text-to-SQL domain. Our best agent, evolved to 1500 lines over 18 iterations, autonomously discovered strategies such as size-adaptive database analysis that adjusts depth based on schema complexity and SQL generation patterns for column selection, evidence interpretation, and aggregation. Evolution provides the largest gains on cheaper models: while we improve by 2.3 points over a strong Claude Opus 4.5 naive baseline, we show an improvement of 8.9 points over the weaker Claude Haiku model. This enables 'skip a tier' deployment: evolved Haiku exceeds naive Sonnet accuracy, and evolved Sonnet exceeds naive Opus, both at lower cost. The full system achieves 73.67% accuracy on the BIRD test set, demonstrating that AI can autonomously build a strong agentic system with only a trivial human-provided starting point.

Formulating optimization problems for industrial applications demands significant manual effort and domain expertise. While Large Language Models (LLMs) show promise in automating this process, evaluating their performance remains difficult due to the absence of robust metrics. Existing solver-based approaches often face inconsistency, infeasibility issues, and high computational costs. To address these issues, we propose ORGEval, a graph-theoretic evaluation framework for assessing LLMs' capabilities in formulating linear and mixed-integer linear programs. ORGEval represents optimization models as graphs, reducing equivalence detection to graph isomorphism testing. We identify and prove a sufficient condition, when the tested graphs are symmetric decomposable (SD), under which the Weisfeiler-Lehman (WL) test is guaranteed to correctly detect isomorphism. Building on this, ORGEval integrates a tailored variant of the WL-test with an SD detection algorithm to evaluate model equivalence. By focusing on structural equivalence rather than instance-level configurations, ORGEval is robust to numerical variations. Experimental results show that our method can successfully detect model equivalence and produce 100\% consistent results across random parameter configurations, while significantly outperforming solver-based methods in runtime, especially on difficult problems. Leveraging ORGEval, we construct the Bench4Opt dataset and benchmark state-of-the-art LLMs on optimization modeling. Our results reveal that although optimization modeling remains challenging for all LLMs, DeepSeek-V3 and Claude-Opus-4 achieve the highest accuracies under direct prompting, outperforming even leading reasoning models.

A significant portion of the textual data used in the field of Natural Language Processing (NLP) exhibits gender biases, particularly due to the use of masculine generics (masculine words that are supposed to refer to mixed groups of men and women), which can perpetuate and amplify stereotypes. Gender rewriting, an NLP task that involves automatically detecting and replacing gendered forms with neutral or opposite forms (e.g., from masculine to feminine), can be employed to mitigate these biases. While such systems have been developed in a number of languages (English, Arabic, Portuguese, German, French), automatic use of gender neutralization techniques (as opposed to inclusive or gender-switching techniques) has only been studied for English. This paper presents GeNRe, the very first French gender-neutral rewriting system using collective nouns, which are gender-fixed in French. We introduce a rule-based system (RBS) tailored for the French language alongside two fine-tuned language models trained on data generated by our RBS. We also explore the use of instruct-based models to enhance the performance of our other systems and find that Claude 3 Opus combined with our dictionary achieves results close to our RBS. Through this contribution, we hope to promote the advancement of gender bias mitigation techniques in NLP for French.

This paper presents a novel framework for enhancing reasoning capabilities in large language models (LLMs) by leveraging iterative reasoning and feedback-driven methodologies. Building on the limitations identified in the SimpleBench benchmark, a dataset designed to evaluate logical coherence and real-world reasoning, we propose a multi-step prompting strategy coupled with global consistency checks to improve model accuracy and robustness. Through comparative analysis of state-of-the-art models, including Claude 3 Opus, Claude 3.5, GPT- 4o, and o1-preview, we demonstrate that iterative reasoning significantly enhances model performance, with improvements observed in both standard accuracy metrics (AVG@5) and a newly introduced metric, Extreme Averaging (EAG@5). Our results reveal model-specific strengths: Claude excels in maintaining logical consistency, while GPT-4o exhibits exploratory creativity but struggles with ambiguous prompts. By analyzing case studies and identifying gaps in spatial and temporal reasoning, we highlight areas for further refinement. The findings underscore the potential of structured reasoning frameworks to address inherent model limitations, irrespective of pretraining methodologies. This study lays the groundwork for integrating dynamic feedback mechanisms, adaptive restart strategies, and diverse evaluation metrics to advance LLM reasoning capabilities across complex and multi-domain problem spaces.

Large language models (LLMs) are increasingly utilized to assist in scientific and academic writing, helping authors enhance the coherence of their articles. Previous studies have highlighted stereotypes and biases present in LLM outputs, emphasizing the need to evaluate these models for their alignment with human narrative styles and potential gender biases. In this study, we assess the alignment of three prominent LLMs - Claude 3 Opus, Mistral AI Large, and Gemini 1.5 Flash - by analyzing their performance on benchmark text-generation tasks for scientific abstracts. We employ the Linguistic Inquiry and Word Count (LIWC) framework to extract lexical, psychological, and social features from the generated texts. Our findings indicate that, while these models generally produce text closely resembling human authored content, variations in stylistic features suggest significant gender biases. This research highlights the importance of developing LLMs that maintain a diversity of writing styles to promote inclusivity in academic discourse.

The paper presents the performance results of Reactor Mk.1, ARCs flagship large language model, through a benchmarking process analysis. The model utilizes the Lychee AI engine and possesses less than 100 billion parameters, resulting in a combination of efficiency and potency. The Reactor Mk.1 outperformed models such as GPT-4o, Claude Opus, and Llama 3, with achieved scores of 92% on the MMLU dataset, 91% on HumanEval dataset, and 88% on BBH dataset. It excels in both managing difficult jobs and reasoning, establishing as a prominent AI solution in the present cutting-edge AI technology.

The disaggregation of the Radio Access Network (RAN) introduces unprecedented flexibility but significant operational complexity, necessitating automated management frameworks. However, current Open RAN (O-RAN) orchestration relies on fragmented manual policies, lacking end-to-end intent assurance from high-level requirements to low-level configurations. In this paper, we propose ORION, an O-RAN compliant intent orchestration framework that integrates Large Language Models (LLMs) via the Model Context Protocol (MCP) to translate natural language intents into enforceable network policies. ORION leverages a hierarchical agent architecture, combining an MCP-based Service Management and Orchestration (SMO) layer for semantic translation with a Non-Real-Time RIC rApp and Near-Real-Time RIC xApp for closed-loop enforcement. Extensive evaluations using GPT-5, Gemini 3 Pro, and Claude Opus demonstrate a 100% policy generation success rate for high-capacity models, highlighting significant trade-offs in reasoning efficiency. We show that ORION reduces provisioning complexity by automating the complete intent lifecycle, from ingestion to E2-level enforcement, paving the way for autonomous 6G networks.

Commercial large language models (LLMs), like OpenAI's GPT-4 powering ChatGPT and Anthropic's Claude 3 Opus, have dominated natural language processing (NLP) benchmarks across different domains. New competing Open-Source alternatives like Mixtral 8x7B or Llama 3 have emerged and seem to be closing the gap while often offering higher throughput and being less costly to use. Open-Source LLMs can also be self-hosted, which makes them interesting for enterprise and clinical use cases where sensitive data should not be processed by third parties. We participated in the 12th BioASQ challenge, which is a retrieval augmented generation (RAG) setting, and explored the performance of current GPT models Claude 3 Opus, GPT-3.5-turbo and Mixtral 8x7b with in-context learning (zero-shot, few-shot) and QLoRa fine-tuning. We also explored how additional relevant knowledge from Wikipedia added to the context-window of the LLM might improve their performance. Mixtral 8x7b was competitive in the 10-shot setting, both with and without fine-tuning, but failed to produce usable results in the zero-shot setting. QLoRa fine-tuning and Wikipedia context did not lead to measurable performance gains. Our results indicate that the performance gap between commercial and open-source models in RAG setups exists mainly in the zero-shot setting and can be closed by simply collecting few-shot examples for domain-specific use cases. The code needed to rerun these experiments is available through GitHub.

Challenging the prevailing consensus that small models inherently lack robust reasoning, this report introduces VibeThinker-1.5B, a 1.5B-parameter dense model developed via our Spectrum-to-Signal Principle (SSP). This challenges the prevailing approach of scaling model parameters to enhance capabilities, as seen in models like DeepSeek R1 (671B) and Kimi k2 (>1T). The SSP framework first employs a Two-Stage Diversity-Exploring Distillation (SFT) to generate a broad spectrum of solutions, followed by MaxEnt-Guided Policy Optimization (RL) to amplify the correct signal. With a total training cost of only $7,800, VibeThinker-1.5B demonstrates superior reasoning capabilities compared to closed-source models like Magistral Medium and Claude Opus 4, and performs on par with open-source models like GPT OSS-20B Medium. Remarkably, it surpasses the 400x larger DeepSeek R1 on three math benchmarks: AIME24 (80.3 vs. 79.8), AIME25 (74.4 vs. 70.0), and HMMT25 (50.4 vs. 41.7). This is a substantial improvement over its base model (6.7, 4.3, and 0.6, respectively). On LiveCodeBench V6, it scores 51.1, outperforming Magistral Medium's 50.3 and its base model's 0.0. These findings demonstrate that small models can achieve reasoning capabilities comparable to large models, drastically reducing training and inference costs and thereby democratizing advanced AI research.

Following the recent achievement of gold-medal performance on the IMO by frontier LLMs, the community is searching for the next meaningful and challenging target for measuring LLM reasoning. Whereas olympiad-style problems measure step-by-step reasoning alone, research-level problems use such reasoning to advance the frontier of mathematical knowledge itself, emerging as a compelling alternative. Yet research-level math benchmarks remain scarce because such problems are difficult to source (e.g., Riemann Bench and FrontierMath-Tier 4 contain 25 and 50 problems, respectively). To support reliable evaluation of next-generation frontier models, we introduce Soohak, a 439-problem benchmark newly authored from scratch by 64 mathematicians. Soohak comprises two subsets. On the Challenge subset, frontier models including Gemini-3-Pro, GPT-5, and Claude-Opus-4.5 reach 30.4%, 26.4%, and 10.4% respectively, leaving substantial headroom, while leading open-weight models such as Qwen3-235B, GPT-OSS-120B, and Kimi-2.5 remain below 15%. Notably, beyond standard problem solving, Soohak introduces a refusal subset that probes a capability intrinsic to research mathematics: recognizing ill-posed problems and pausing rather than producing confident but unjustified answers. On this subset, no model exceeds 50%, identifying refusal as a new optimization target that current models do not directly address. To prevent contamination, the dataset will be publicly released in late 2026, with model evaluations available upon request in the interim.

We present DeepSeek-Coder-V2, an open-source Mixture-of-Experts (MoE) code language model that achieves performance comparable to GPT4-Turbo in code-specific tasks. Specifically, DeepSeek-Coder-V2 is further pre-trained from an intermediate checkpoint of DeepSeek-V2 with additional 6 trillion tokens. Through this continued pre-training, DeepSeek-Coder-V2 substantially enhances the coding and mathematical reasoning capabilities of DeepSeek-V2, while maintaining comparable performance in general language tasks. Compared to DeepSeek-Coder-33B, DeepSeek-Coder-V2 demonstrates significant advancements in various aspects of code-related tasks, as well as reasoning and general capabilities. Additionally, DeepSeek-Coder-V2 expands its support for programming languages from 86 to 338, while extending the context length from 16K to 128K. In standard benchmark evaluations, DeepSeek-Coder-V2 achieves superior performance compared to closed-source models such as GPT4-Turbo, Claude 3 Opus, and Gemini 1.5 Pro in coding and math benchmarks.

Agent skills, which are reusable, domain-specific knowledge artifacts, have become a popular mechanism for extending LLM-based agents, yet formally benchmarking skill usage performance remains scarce. Existing skill benchmarking efforts focus on overly idealized conditions, where LLMs are directly provided with hand-crafted, narrowly-tailored task-specific skills for each task, whereas in many realistic settings, the LLM agent may have to search for and select relevant skills on its own, and even the closest matching skills may not be well-tailored for the task. In this paper, we conduct the first comprehensive study of skill utility under progressively challenging realistic settings, where agents must retrieve skills from a large collection of 34k real-world skills and may not have access to any hand-curated skills. Our findings reveal that the benefits of skills are fragile: performance gains degrade consistently as settings become more realistic, with pass rates approaching no-skill baselines in the most challenging scenarios. To narrow this gap, we study skill refinement strategies, including query-specific and query-agnostic approaches, and we show that query-specific refinement substantially recovers lost performance when the initial skills are of reasonable relevance and quality. We further demonstrate the generality of retrieval and refinement on Terminal-Bench 2.0, where they improve the pass rate of Claude Opus 4.6 from 57.7% to 65.5%. Our results, consistent across multiple models, highlight both the promise and the current limitations of skills for LLM-based agents. Our code is available at https://github.com/UCSB-NLP-Chang/Skill-Usage.

Large language models are prominently used in real-world applications, often tasked with reasoning over large volumes of documents. An exciting development in this space is models boasting extended context capabilities, with some accommodating over 2 million tokens. Such long context model capabilities remain uncertain in production systems, motivating the need to benchmark their performance on real world use cases. We address this challenge by proposing SWiM, an evaluation framework that addresses the limitations of standard tests. Testing the framework on eight long context models, we find that even strong models such as GPT-4 and Claude 3 Opus degrade in performance when information is present in the middle of the context window (lost-in-the-middle effect). Next, in addition to our benchmark, we propose medoid voting, a simple, but effective training-free approach that helps alleviate this effect, by generating responses a few times, each time randomly permuting documents in the context, and selecting the medoid answer. We evaluate medoid voting on single document QA tasks, achieving up to a 24% lift in accuracy.

Direct Preference Optimization (DPO) is a widely used offline preference optimization algorithm that reparameterizes reward functions in reinforcement learning from human feedback (RLHF) to enhance simplicity and training stability. In this work, we propose SimPO, a simpler yet more effective approach. The effectiveness of SimPO is attributed to a key design: using the average log probability of a sequence as the implicit reward. This reward formulation better aligns with model generation and eliminates the need for a reference model, making it more compute and memory efficient. Additionally, we introduce a target reward margin to the Bradley-Terry objective to encourage a larger margin between the winning and losing responses, further enhancing the algorithm's performance. We compare SimPO to DPO and its latest variants across various state-of-the-art training setups, including both base and instruction-tuned models like Mistral and Llama3. We evaluated on extensive instruction-following benchmarks, including AlpacaEval 2, MT-Bench, and the recent challenging Arena-Hard benchmark. Our results demonstrate that SimPO consistently and significantly outperforms existing approaches without substantially increasing response length. Specifically, SimPO outperforms DPO by up to 6.4 points on AlpacaEval 2 and by up to 7.5 points on Arena-Hard. Our top-performing model, built on Llama3-8B-Instruct, achieves a remarkable 44.7 length-controlled win rate on AlpacaEval 2 -- surpassing Claude 3 Opus on the leaderboard, and a 33.8 win rate on Arena-Hard -- making it the strongest 8B open-source model.

With the advancement of AI capabilities, AI reviewers are beginning to be deployed in scientific peer review, yet their capability and credibility remain in question: many scientists simply view them as probabilistic systems without the expertise to evaluate research, while other researchers are more optimistic about their readiness without concrete evidence. Understanding what AI reviewers do well, where they fall short, and what challenges remain is essential. However, existing evaluations of AI reviewers have focused on whether their verdicts match human verdicts (e.g., score alignment, acceptance prediction), which is insufficient to characterize their capabilities and limits. In this paper, we close this gap through a large-scale expert annotation study, in which 45 domain scientists in Physical, Biological, and Health Sciences spent 469 hours rating 2,960 individual criticisms (each targeting one specific aspect of a paper) from human-written and AI-generated reviews of 82 Nature-family papers on correctness, significance, and sufficiency of evidence. On a composite of all three dimensions, a reviewing agent powered by GPT-5.2 scores above each paper's top-rated human reviewer (60.0% vs. 48.2%, p = 0.009), while all three AI reviewers (including Gemini 3.0 Pro and Claude Opus 4.5) exceed the lowest-rated human across every dimension. AI reviewers' accurate criticisms are also more often rated significant and well-evidenced, and surface a distinct 26% of issues no human raises. However, AI reviewers overlap far more than humans do (21% vs. 3% for cross-reviewer pairs), and exhibit 16 recurring weaknesses humans do not share, such as limited subfield knowledge, lack of long context management over multiple files, and overly critical stance on minor issues. Overall, our results position current AI reviewers as complements to, not substitutes for, human reviewers.

We introduce LLM-Wikirace, a benchmark for evaluating planning, reasoning, and world knowledge in large language models (LLMs). In LLM-Wikirace, models must efficiently navigate Wikipedia hyperlinks step by step to reach a target page from a given source, requiring look-ahead planning and the ability to reason about how concepts are connected in the real world. We evaluate a broad set of open- and closed-source models, including Gemini-3, GPT-5, and Claude Opus 4.5, which achieve the strongest results on the easy level of the task and demonstrate superhuman performance. Despite this, performance drops sharply on hard difficulty: the best-performing model, Gemini-3, succeeds in only 23\% of hard games, highlighting substantial remaining challenges for frontier models. Our analysis shows that world knowledge is a necessary ingredient for success, but only up to a point, beyond this threshold, planning and long-horizon reasoning capabilities become the dominant factors. Trajectory-level analysis further reveals that even the strongest models struggle to replan after failure, frequently entering loops rather than recovering. LLM-Wikirace is a simple benchmark that reveals clear limitations in current reasoning systems, offering an open arena where planning-capable LLMs still have much to prove. Our code and leaderboard available at https:/llmwikirace.github.io.

We introduce SafeWork-R1, a cutting-edge multimodal reasoning model that demonstrates the coevolution of capabilities and safety. It is developed by our proposed SafeLadder framework, which incorporates large-scale, progressive, safety-oriented reinforcement learning post-training, supported by a suite of multi-principled verifiers. Unlike previous alignment methods such as RLHF that simply learn human preferences, SafeLadder enables SafeWork-R1 to develop intrinsic safety reasoning and self-reflection abilities, giving rise to safety `aha' moments. Notably, SafeWork-R1 achieves an average improvement of 46.54% over its base model Qwen2.5-VL-72B on safety-related benchmarks without compromising general capabilities, and delivers state-of-the-art safety performance compared to leading proprietary models such as GPT-4.1 and Claude Opus 4. To further bolster its reliability, we implement two distinct inference-time intervention methods and a deliberative search mechanism, enforcing step-level verification. Finally, we further develop SafeWork-R1-InternVL3-78B, SafeWork-R1-DeepSeek-70B, and SafeWork-R1-Qwen2.5VL-7B. All resulting models demonstrate that safety and capability can co-evolve synergistically, highlighting the generalizability of our framework in building robust, reliable, and trustworthy general-purpose AI.

Comprehending text-rich visual content is paramount for the practical application of Multimodal Large Language Models (MLLMs), since text-rich scenarios are ubiquitous in the real world, which are characterized by the presence of extensive texts embedded within images. Recently, the advent of MLLMs with impressive versatility has raised the bar for what we can expect from MLLMs. However, their proficiency in text-rich scenarios has yet to be comprehensively and objectively assessed, since current MLLM benchmarks primarily focus on evaluating general visual comprehension. In this work, we introduce SEED-Bench-2-Plus, a benchmark specifically designed for evaluating text-rich visual comprehension of MLLMs. Our benchmark comprises 2.3K multiple-choice questions with precise human annotations, spanning three broad categories: Charts, Maps, and Webs, each of which covers a wide spectrum of text-rich scenarios in the real world. These categories, due to their inherent complexity and diversity, effectively simulate real-world text-rich environments. We further conduct a thorough evaluation involving 34 prominent MLLMs (including GPT-4V, Gemini-Pro-Vision and Claude-3-Opus) and emphasize the current limitations of MLLMs in text-rich visual comprehension. We hope that our work can serve as a valuable addition to existing MLLM benchmarks, providing insightful observations and inspiring further research in the area of text-rich visual comprehension with MLLMs. The dataset and evaluation code can be accessed at https://github.com/AILab-CVC/SEED-Bench.

We introduce CurveBench, a benchmark for hierarchical topological reasoning from visual input. CurveBench consists of 756 images of pairwise non-intersecting Jordan curves across easy, polygonal, topographic-inspired, maze-like, and dense counting configurations. Each image is annotated with a rooted tree encoding the containment relations between planar regions. We formulate the task as structured prediction: given an image, a model must recover the full rooted containment tree induced by the curves. Despite the visual simplicity of the task, the strongest evaluated model, Gemini 3.1 Pro, achieves only 71.1\% tree-generation accuracy on CurveBench-Easy and 19.1\% on CurveBench-Hard. We further demonstrate benchmark utility through RLVR-style fine-tuning of open-weight vision-language models. Our trained Qwen3-VL-8B model improves over Qwen-3-VL-8B-Thinking from 2.8\% to 33.3\% tree-generation accuracy on CurveBench-Easy, exceeding GPT-5.4 and Claude Opus 4.5 under our evaluation protocol. The remaining gap, especially on CurveBench-Hard, shows that exact topology-aware visual reasoning remains far from solved.

Accurately understanding the intent behind speech, conversation, and writing is crucial to the development of helpful Large Language Model (LLM) assistants. This paper introduces IntentGrasp, a comprehensive benchmark for evaluating the intent understanding capability of LLMs. Derived from 49 high-quality, open-licensed corpora spanning 12 diverse domains, IntentGrasp is constructed through source datasets curation, intent label contextualization, and task format unification. IntentGrasp contains a large-scale training set of 262,759 instances and two evaluation sets: an All Set of 12,909 test cases and a more balanced and challenging Gem Set of 470 cases. Extensive evaluations on 20 LLMs across 7 families (including frontier models such as GPT-5.4, Gemini-3.1-Pro, and Claude-Opus-4.7) demonstrate unsatisfactory performance, with scores below 60% on All Set and below 25% on Gem set. Notably, 17 out of 20 tested models perform worse than a random-guess baseline (15.2%) on Gem Set, while the estimated human performance is ~81.1%, showing substantial room for improvement. To enhance such ability, this paper proposes Intentional Fine-Tuning (IFT), which fine-tunes the models on the training set in IntentGrasp, yielding significant gains of 30+ F1 points on All Set and 20+ points on Gem Set. Tellingly, the leave-one-domain-out (Lodo) experiments further demonstrate the strong cross-domain generalizability of IFT, verifying that it is a promising approach to substantially enhancing the intent understanding of LLMs. Overall, by benchmarking and boosting intent understanding ability, this study sheds light on a promising path towards more intentional, capable, and safe AI assistants for human benefits and social good.

Monitoring complex industrial assets relies on engineer-authored symbolic rules that trigger based on sensor conditions and prompt technicians to perform corrective actions. The bottleneck is not detection but response: translating rules into maintenance steps requires asset-specific knowledge gained through years of practice. We investigate whether LLMs can serve as decision support for this rule-to-action step and introduce , a benchmark of 6{,}690 expert-validated multiple-choice questions from 118 rule-action pairs across 16 asset types. We contribute (i) a symbolic-to-MCQA pipeline normalizing rules to Disjunctive Normal Form with embedding-based distractor sampling, (ii) five variants probing distinct failure modes (Pro, Pert, Verbose, Aug, Rationale), and (iii) a benchmark of 29 LLMs and 4 embedding baselines. A human evaluation (9 practitioners, mean 45.0\%) confirms requires specialist knowledge beyond operational experience. Three findings stand out. The frontier has closed: the top three LLMs lie within one Macro point, with Bradley-Terry Elo placing claude-opus-4-6 30 points above the next model. Yet \,Pro exposes brittleness, with every model losing 13--60\% relative accuracy under distractor expansion. \,Aug exposes pattern-matching: under condition inversion, frontier models still select the original answer 49--63\% of the time. The deployment bottleneck is not capability but calibration: frontier models handle template-style fault detection but break under structural perturbation.

Enabling Large Language Models (LLMs) to reliably invoke external tools remains a critical bottleneck for autonomous agents. Existing approaches suffer from three fundamental challenges: expensive human annotation for high-quality trajectories, poor generalization to unseen tools, and quality ceilings inherent in single-model synthesis that perpetuate biases and coverage gaps. We introduce InfTool, a fully autonomous framework that breaks these barriers through self-evolving multi-agent synthesis. Given only raw API specifications, InfTool orchestrates three collaborative agents (User Simulator, Tool-Calling Assistant, and MCP Server) to generate diverse, verified trajectories spanning single-turn calls to complex multi-step workflows. The framework establishes a closed loop: synthesized data trains the model via Group Relative Policy Optimization (GRPO) with gated rewards, the improved model generates higher-quality data targeting capability gaps, and this cycle iterates without human intervention. Experiments on the Berkeley Function-Calling Leaderboard (BFCL) demonstrate that InfTool transforms a base 32B model from 19.8% to 70.9% accuracy (+258%), surpassing models 10x larger and rivaling Claude-Opus, and entirely from synthetic data without human annotation.

Entropy minimization (EM) trains the model to concentrate even more probability mass on its most confident outputs. We show that this simple objective alone, without any labeled data, can substantially improve large language models' (LLMs) performance on challenging math, physics, and coding tasks. We explore three approaches: (1) EM-FT minimizes token-level entropy similarly to instruction finetuning, but on unlabeled outputs drawn from the model; (2) EM-RL: reinforcement learning with negative entropy as the only reward to maximize; (3) EM-INF: inference-time logit adjustment to reduce entropy without any training data or parameter updates. On Qwen-7B, EM-RL, without any labeled data, achieves comparable or better performance than strong RL baselines such as GRPO and RLOO that are trained on 60K labeled examples. Furthermore, EM-INF enables Qwen-32B to match or exceed the performance of proprietary models like GPT-4o, Claude 3 Opus, and Gemini 1.5 Pro on the challenging SciCode benchmark, while being 3x more efficient than self-consistency and sequential refinement. Our findings reveal that many pretrained LLMs possess previously underappreciated reasoning capabilities that can be effectively elicited through entropy minimization alone, without any labeled data or even any parameter updates.

Even though large language models are becoming increasingly capable, it is still unreasonable to expect them to excel at tasks that are under-represented on the Internet. Leveraging LLMs for specialized applications, particularly in niche programming languages and private domains, remains challenging and largely unsolved. In this work, we address this gap by presenting a comprehensive, open-source approach for adapting LLMs to the Q programming language, a popular tool in quantitative finance that is much less present on the Internet compared to Python, C, Java, and other ``mainstream" languages and is therefore not a strong suit of general-purpose AI models. We introduce a new Leetcode style evaluation dataset for Q, benchmark major frontier models on the dataset, then do pretraining, supervised fine tuning, and reinforcement learning to train a suite of reasoning and non-reasoning models based on the Qwen-2.5 series, spanning five parameter sizes (1.5B, 3B, 7B, 14B, 32B). Our best model achieves a pass@1 accuracy of 59 percent on our Q benchmark, surpassing the best-performing frontier model, Claude Opus-4 by 29.5 percent. Additionally, all models, even our 1.5B model, outperform GPT-4.1 on this task. In addition to releasing models, code, and data, we provide a detailed blueprint for dataset construction, model pretraining, supervised fine-tuning, and reinforcement learning. Our methodology is broadly applicable, and we discuss how these techniques can be extended to other tasks, including those where evaluation may rely on soft or subjective signals.

Language Model (LM) agents for cybersecurity that are capable of autonomously identifying vulnerabilities and executing exploits have the potential to cause real-world impact. Policymakers, model providers, and other researchers in the AI and cybersecurity communities are interested in quantifying the capabilities of such agents to help mitigate cyberrisk and investigate opportunities for penetration testing. Toward that end, we introduce Cybench, a framework for specifying cybersecurity tasks and evaluating agents on those tasks. We include 40 professional-level Capture the Flag (CTF) tasks from 4 distinct CTF competitions, chosen to be recent, meaningful, and spanning a wide range of difficulties. Each task includes its own description, starter files, and is initialized in an environment where an agent can execute bash commands and observe outputs. Since many tasks are beyond the capabilities of existing LM agents, we introduce subtasks, which break down a task into intermediary steps for more gradated evaluation; we add subtasks for 17 of the 40 tasks. To evaluate agent capabilities, we construct a cybersecurity agent and evaluate 7 models: GPT-4o, Claude 3 Opus, Claude 3.5 Sonnet, Mixtral 8x22b Instruct, Gemini 1.5 Pro, Llama 3 70B Chat, and Llama 3.1 405B Instruct. Without guidance, we find that agents are able to solve only the easiest complete tasks that took human teams up to 11 minutes to solve, with Claude 3.5 Sonnet and GPT-4o having the highest success rates. Finally, subtasks provide more signal for measuring performance compared to unguided runs, with models achieving a 3.2\% higher success rate on complete tasks with subtask-guidance than without subtask-guidance. All code and data are publicly available at https://cybench.github.io

As Large Language Models (LLMs) saturate elementary benchmarks, the research frontier has shifted from generation to the reliability of automated evaluation. We demonstrate that standard "LLM-as-a-Judge" protocols suffer from a systematic Alignment Gap when applied to upper-undergraduate to early graduate level mathematics. To quantify this, we introduce QEDBench, the first large-scale dual-rubric alignment benchmark to systematically measure alignment with human experts on university-level math proofs by contrasting course-specific rubrics against expert common knowledge criteria. By deploying a dual-evaluation matrix (7 judges x 5 solvers) against 1,000+ hours of human evaluation, we reveal that certain frontier evaluators like Claude Opus 4.5, DeepSeek-V3, Qwen 2.5 Max, and Llama 4 Maverick exhibit significant positive bias (up to +0.18, +0.20, +0.30, +0.36 mean score inflation, respectively). Furthermore, we uncover a critical reasoning gap in the discrete domain: while Gemini 3.0 Pro achieves state-of-the-art performance (0.91 average human evaluation score), other reasoning models like GPT-5 Pro and Claude Sonnet 4.5 see their performance significantly degrade in discrete domains. Specifically, their average human evaluation scores drop to 0.72 and 0.63 in Discrete Math, and to 0.74 and 0.50 in Graph Theory. In addition to these research results, we also release QEDBench as a public benchmark for evaluating and improving AI judges. Our benchmark is publicly published at https://github.com/qqliu/Yale-QEDBench.

Direct Preference Optimization (DPO) has emerged as a cornerstone of reinforcement learning from human feedback (RLHF) due to its simplicity and efficiency. However, existing DPO-based methods typically treat all preference pairs equally, overlooking substantial variations in data quality and learning difficulty, which leads to inefficient data utilization and suboptimal performance. To address this limitation, we propose Uni-DPO, a unified dynamic preference optimization framework that jointly considers (a) the inherent quality of preference pairs and (b) the model's evolving performance during training. By adaptively reweighting samples based on both factors, Uni-DPO enables more effective use of preference data and achieves superior performance. Extensive experiments across models and benchmarks demonstrate the effectiveness and generalization of Uni-DPO. On textual tasks, Gemma-2-9B-IT fine-tuned with Uni-DPO surpasses the leading LLM, Claude 3 Opus, by 6.7 points on Arena-Hard. On mathematical and multimodal tasks, Uni-DPO consistently outperforms baseline methods across all benchmarks, providing strong empirical evidence of its effectiveness and robustness.

Current benchmarks for assessing vision-language models (VLMs) often focus on their perception or problem-solving capabilities and neglect other critical aspects such as fairness, multilinguality, or toxicity. Furthermore, they differ in their evaluation procedures and the scope of the evaluation, making it difficult to compare models. To address these issues, we extend the HELM framework to VLMs to present the Holistic Evaluation of Vision Language Models (VHELM). VHELM aggregates various datasets to cover one or more of the 9 aspects: visual perception, knowledge, reasoning, bias, fairness, multilinguality, robustness, toxicity, and safety. In doing so, we produce a comprehensive, multi-dimensional view of the capabilities of the VLMs across these important factors. In addition, we standardize the standard inference parameters, methods of prompting, and evaluation metrics to enable fair comparisons across models. Our framework is designed to be lightweight and automatic so that evaluation runs are cheap and fast. Our initial run evaluates 22 VLMs on 21 existing datasets to provide a holistic snapshot of the models. We uncover new key findings, such as the fact that efficiency-focused models (e.g., Claude 3 Haiku or Gemini 1.5 Flash) perform significantly worse than their full models (e.g., Claude 3 Opus or Gemini 1.5 Pro) on the bias benchmark but not when evaluated on the other aspects. For transparency, we release the raw model generations and complete results on our website (https://crfm.stanford.edu/helm/vhelm/v2.0.1). VHELM is intended to be a living benchmark, and we hope to continue adding new datasets and models over time.

While long-context large language models (LLMs) can technically summarize book-length documents (>100K tokens), the length and complexity of the documents have so far prohibited evaluations of input-dependent aspects like faithfulness. In this paper, we conduct the first large-scale human evaluation of faithfulness and content selection on LLM-generated summaries of fictional books. Our study mitigates the issue of data contamination by focusing on summaries of books published in 2023 or 2024, and we hire annotators who have fully read each book prior to the annotation task to minimize cost and cognitive burden. We collect FABLES, a dataset of annotations on 3,158 claims made in LLM-generated summaries of 26 books, at a cost of $5.2K USD, which allows us to rank LLM summarizers based on faithfulness: Claude-3-Opus significantly outperforms all closed-source LLMs, while the open-source Mixtral is on par with GPT-3.5-Turbo. An analysis of the annotations reveals that most unfaithful claims relate to events and character states, and they generally require indirect reasoning over the narrative to invalidate. While LLM-based auto-raters have proven reliable for factuality and coherence in other settings, we implement several LLM raters of faithfulness and find that none correlates strongly with human annotations, especially with regard to detecting unfaithful claims. Our experiments suggest that detecting unfaithful claims is an important future direction not only for summarization evaluation but also as a testbed for long-context understanding. Finally, we move beyond faithfulness by exploring content selection errors in book-length summarization: we develop a typology of omission errors related to crucial narrative elements and also identify a systematic over-emphasis on events occurring towards the end of the book.

We introduce the AI Productivity Index for Agents (APEX-Agents), a benchmark for assessing whether AI agents can execute long-horizon, cross-application tasks created by investment banking analysts, management consultants, and corporate lawyers. APEX-Agents requires agents to navigate realistic work environments with files and tools. We test eight agents for the leaderboard using Pass@1. Gemini 3 Flash (Thinking=High) achieves the highest score of 24.0%, followed by GPT-5.2 (Thinking=High), Claude Opus 4.5 (Thinking=High), and Gemini 3 Pro (Thinking=High). We open source the APEX-Agents benchmark (n=480) with all prompts, rubrics, gold outputs, files, and metadata. We also open-source Archipelago, our infrastructure for agent execution and evaluation.

The advancement of LLM agents with tool-use capabilities requires diverse and complex training corpora. Existing data generation methods, which predominantly follow a paradigm of random sampling and shallow generation, often yield simple and homogeneous trajectories that fail to capture complex, implicit logical dependencies. To bridge this gap, we introduce HardGen, an automatic agentic pipeline designed to generate hard tool-use training samples with verifiable reasoning. Firstly, HardGen establishes a dynamic API Graph built upon agent failure cases, from which it samples to synthesize hard traces. Secondly, these traces serve as conditional priors to guide the instantiation of modular, abstract advanced tools, which are subsequently leveraged to formulate hard queries. Finally, the advanced tools and hard queries enable the generation of verifiable complex Chain-of-Thought (CoT), with a closed-loop evaluation feedback steering the continuous refinement of the process. Extensive evaluations demonstrate that a 4B parameter model trained with our curated dataset achieves superior performance compared to several leading open-source and closed-source competitors (e.g., GPT-5.2, Gemini-3-Pro and Claude-Opus-4.5). Our code, models, and dataset will be open-sourced to facilitate future research.

Large Language Models (LLMs) are widely used as judges to evaluate response quality, providing a scalable alternative to human evaluation. However, most LLM judges operate solely on intrinsic text-based reasoning, limiting their ability to verify complex constraints or perform accurate computation. Motivated by the success of tool-integrated reasoning (TIR) in numerous tasks, we propose TIR-Judge, an end-to-end RL framework for training LLM judges that integrates a code executor for precise evaluation. TIR-Judge is built on three principles: (i) diverse training across verifiable and non-verifiable domains, (ii) flexible judgment formats (pointwise, pairwise, listwise), and (iii) iterative RL that bootstraps directly from the initial model without distillation. On seven public benchmarks, TIR-Judge surpasses strong reasoning-based judges by up to 6.4% (pointwise) and 7.7% (pairwise), and achieves listwise performance comparable to Claude-Opus-4 despite having only 8B parameters. Remarkably, TIR-Judge-Zero - trained entirely without distilled judge trajectories, matches the performance of distilled variants, demonstrating that tool-augmented judges can self-evolve through iterative reinforcement learning.

We introduce ShapeCodeBench, a synthetic benchmark for perception-to-program reconstruction: given a rendered raster image, a model must emit an executable drawing program that a deterministic evaluator re-renders and compares with the target. The v1 DSL has four primitives on a 512 x 512 black-on-white canvas, but every instance is generated from a seeded RNG, so fresh held-out sets can be created to reduce exact-instance contamination. We release a frozen eval_v1 split with 150 samples across easy, medium, and hard tiers, scored by exact match, pixel accuracy, foreground IoU, parse success, and execution success. We evaluate an empty-program floor, a classical computer-vision heuristic, Claude Opus 4.7 at high and max effort, and GPT-5.5 at medium and extra_high reasoning effort. The heuristic is competitive on easy scenes but collapses when overlaps fuse components; the strongest multimodal configuration preserves much of the foreground structure but still misses exact match because of small parameter errors. Best overall exact match remains low, so ShapeCodeBench is far from saturated. The benchmark code, frozen dataset, run artifacts, and paper sources are released to support independent replication and extension.

Multimodal large language models (MLLMs) have shown promising reasoning abilities, yet evaluating their performance in specialized domains remains challenging. STEM reasoning is a particularly valuable testbed because it provides highly verifiable feedback, but existing benchmarks often permit unimodal shortcuts due to modality redundancy and focus mainly on final-answer accuracy, overlooking the reasoning process itself. To address this challenge, we introduce StepSTEM: a graduate-level benchmark of 283 problems across mathematics, physics, chemistry, biology, and engineering for fine-grained evaluation of cross-modal reasoning in MLLMs. StepSTEM is constructed through a rigorous curation pipeline that enforces strict complementarity between textual and visual inputs. We further propose a general step-level evaluation framework for both text-only chain-of-thought and interleaved image-text reasoning, using dynamic programming to align predicted reasoning steps with multiple reference solutions. Experiments across a wide range of models show that current MLLMs still rely heavily on textual reasoning, with even Gemini 3.1 Pro and Claude Opus 4.6 achieving only 38.29% accuracy. These results highlight substantial headroom for genuine cross-modal STEM reasoning and position StepSTEM as a benchmark for fine-grained evaluation of multimodal reasoning. Source code is available at https://github.com/lll-hhh/STEPSTEM.

Language models are saturating benchmarks for procedural tasks with narrow objectives. But they are increasingly being deployed in long-horizon, non-stationary environments with open-ended goals. In this paper we introduce KellyBench, an environment for evaluating sequential decision-making in sports betting markets. Agents are placed in a sequential simulation of the 2023-24 English Premier League season and tasked with maximising their long-term bankroll growth. They are given detailed historical data, including advanced statistics, lineups, and public odds. To succeed they must build machine learning models, identify edge in public markets, and adapt as the environment changes over time. We find that all frontier models evaluated lose money on average over the course of the season for five seeds. The best performing model achieves an average return of -8%, and many models experiencing ruin across seeds. To judge strategy sophistication, we use a human expert rubric to grade each model and find their approaches to be unsophisticated compared to human baselines; Claude Opus 4.6 achieves a rubric score of 26.5%, which means there is significant room for improvement. KellyBench is available as an open-access API endpoint at https://openreward.ai/GeneralReasoning/KellyBench.

Discovering causal regularities and applying them to build functional systems--the discovery-to-application loop--is a hallmark of general intelligence, yet evaluating this capacity has been hindered by the vast complexity gap between scientific discovery and real-world engineering. We introduce SciCrafter, a Minecraft-based benchmark that operationalizes this loop through parameterized redstone circuit tasks. Agents must ignite lamps in specified patterns (e.g., simultaneously or in timed sequences); scaling target parameters substantially increases construction complexity and required knowledge, forcing genuine discovery rather than reliance on memorized solutions. Evaluating frontier models including GPT-5.2, Gemini-3-Pro, and Claude-Opus-4.5 under a general-purpose code agent scaffold, we find that all plateau at approximately 26% success rate. To diagnose these failures, we decompose the loop into four capacities--knowledge gap identification, experimental discovery, knowledge consolidation, and knowledge application--and design targeted interventions whose marginal contributions serve as proxies for corresponding gaps. Our analysis reveals that although the general knowledge application capability still remains as the biggest gap across all models, for frontier models the knowledge gap identification starts to become a major hurdle--indicating the bottleneck is shifting from solving problems right to raising the right problems for current AI. We release SciCrafter as a diagnostic probe for future research on AI systems that navigate the full discovery-to-application loop.

As Large Language Models (LLMs) are increasingly proposed for high-stakes medical applications, there has emerged a critical need for reliable and accurate evaluation methodologies. Traditional accuracy metrics fail inadequately as they neither capture question characteristics nor offer topic-specific insights. To address this gap, we introduce MedIRT, a rigorous evaluation framework grounded in Item Response Theory (IRT), the gold standard in high-stakes educational testing. Unlike previous research relying on archival data, we prospectively gathered fresh responses from 80 diverse LLMs on a balanced, 1,100-question USMLE-aligned benchmark. Using one unidimensional two-parameter logistic IRT model per topic, we estimate LLM's latent model ability jointly with question difficulty and discrimination, yielding more stable and nuanced performance rankings than accuracy alone. Notably, we identify distinctive ``spiky'' ability profiles, where overall rankings can be misleading due to highly specialized model abilities. While GPT-5 was the top performer in a majority of domains (8 of 11), it was outperformed in Social Science and Communication by Claude-3-opus, demonstrating that even an overall 23rd-ranked model can hold the top spot for specific competencies. Furthermore, we demonstrate IRT's utility in auditing benchmarks by identifying flawed questions. We synthesize these findings into a practical decision-support framework that integrates our multi-factor competency profiles with operational metrics. This work establishes a robust, psychometrically grounded methodology essential for the safe, effective, and trustworthy deployment of LLMs in healthcare.

Current reinforcement learning (RL) frameworks for large language models (LLM) post-training typically assume a fixed prompt distribution, which is sub-optimal and bottlenecks scalability. Prior works have explored prompt evolving, but are often limited to the supervised fine-tuning stage, and prompts are sampled and evolved uniformly without signals. This empirical work presents a paradigm shift: Evolving Alignment via Asymmetric Self-Play (eva), that casts post-training as an infinite game with regret-based signals for 2 players: (i) a creator, who strategically samples and creates new informative prompts and (ii) a solver, who learns to produce preferred responses. eva is the first method that allows language models to adaptively create training prompts in both offline and online RL post-training. The design is simple, easy-to-use yet remarkably effective: eva sets a new SOTA on challenging benchmarks, without any extra human prompts, e.g. it boosts the win-rate of gemma-2-9b-it on Arena-Hard by 51.6% -> 60.1% for DPO and 52.6% -> 62.4% for RLOO, surpassing claude-3-opus and catching up to gemini-1.5-pro, both of which are orders of magnitude larger. Extensive experiments show eva can create effective RL curricula and is robust across ablations. We believe adaptively evolving prompts are key to designing the next-generation RL post-training scheme.

Frontier large language models are increasingly deployed as orchestration backbones for biological research workflows, yet no shared evidence base exists for comparing their refusal behaviour on legitimate research prompts. RefusalBench, introduced here, is a matched-triple benchmark of 141 prompts in 47 bundles that holds task framing constant while varying only biological risk tier (benign, borderline, dual-use), enabling tier-conditioned comparisons robust to subdomain confounding. A 15-prompt should-refuse positive-control module establishes per-model calibration floors; three models fail to refuse even these prompts. Across 19 frontier models in the May 2026 snapshot, strict refusal rates span 0.1% to 94.6% on identical prompts. Jurisdiction does not predict refusal in this snapshot (Mann-Whitney U, p = 0.393; EU n = 1, US bimodal); provider identity does, with Anthropic's API stack predicting refusal at OR = 21.03 (95% CI: 14.58-30.34 prompt-clustered; 5.70-77.55 under model-clustered GEE). This effect is best read as access-path-level rather than model-weight-level: 99.8% of Anthropic's strict refusals carry the same safety_policy adjudicated reason code, consistent with a small set of canonical refusal templates rather than case-by-case model reasoning. Strict refusal rate misranks safety calibration: Grok 4.20 achieves the highest tier discrimination (Youden's J = 0.787) while ranking only seventh by overall refusal rate, and Claude Opus 4.7's J dropped 65% from prior versions with no improvement in dual-use detection. Nine of 18 frontier models exhibit a hedge-but-help partial-compliance pattern at dual-use tier that binary refusal metrics cannot detect.

The autoresearch repository enables an LLM agent to optimize hyperparameters by editing training code directly. We use it as a testbed to compare classical HPO algorithms against LLM-based methods on tuning the hyperparameters of a small language model under a fixed compute budget. When defining a fixed search space over autoresearch, classical methods such as CMA-ES and TPE consistently outperform LLM-based agents, where avoiding out-of-memory failures matters more than search diversity. Allowing the LLM to directly edit source code narrows the gap to the classical methods but does not close it, even with frontier models available at the time of writing such as Claude Opus 4.6 and Gemini 3.1 Pro Preview. We observe that LLMs struggle to track optimization state across trials. In contrast, classical methods lack the domain knowledge of LLMs. To combine the strengths of both, we introduce Centaur, a hybrid that shares CMA-ES's interpretable internal state, including mean vector, step-size, and covariance matrix, with an LLM. Centaur achieves the best result in our experiments, and a 0.8B LLM already suffices to outperform all classical and pure LLM methods. Unconstrained code editing requires larger models to be competitive with classical methods. We further analyze search diversity, model scaling from 0.8B to frontier models, and ablate the fraction of LLM-proposed trials in Centaur. All in all, our results suggest that LLMs are most effective as a complement to classical optimizers, not as a replacement. Code is available at https://github.com/ferreirafabio/autoresearch-automl & interactive demo at https://ferreirafabio.github.io/autoresearch-automl.

We introduce Pencil Puzzle Bench, a framework for evaluating large language model reasoning through pencil puzzles, a family of constraint-satisfaction problems closely related to NP-complete problems, with deterministic, step-level verification. From a database of 62,231 puzzles across 94 varieties with verified unique solutions, we select a benchmark of 300 puzzles spanning 20 varieties and evaluate 51 models from 11 providers in two modes: direct ask (single-shot) and agentic (multi-turn with iterative verification). A key differentiator of our benchmark is that every intermediate board state can be checked against variety-specific constraints, localizing errors to the exact rule violated, providing the infrastructure for dense, per-move reward signals for process supervision and reinforcement learning. Our evaluation reveals two distinct axes of capability: (1) reasoning effort scaling, where GPT-5.2 improves 81x from no reasoning to maximum effort; and (2) agentic iteration, where Claude Opus 4.6 rises from 0.3% to 30.0% through iterative checking, while GPT-5.2@xhigh improves from 20.2% to 56.0%. Agentic attempts span a median of 29 turns over 17 minutes, with the longest exceeding 1,221 turns and 14.3 hours - a demanding test of long-context utilization, not just reasoning.

Spatial visualization is the mental ability to imagine, transform, and manipulate the spatial characteristics of objects and actions. This intelligence is a part of human cognition where actions and perception are connected on a mental level. To explore whether state-of-the-art Vision-Language Models (VLMs) exhibit this ability, we develop MentalBlackboard, an open-ended spatial visualization benchmark for Paper Folding and Hole Punching tests within two core tasks: prediction and planning. Our prediction experiments reveal that models struggle with applying symmetrical transformations, even when they predict the sequence of unfolding steps correctly. Also, rotations introduce a significant challenge to the physical situational awareness for models. The planning task reveals limitations of models in analyzing symmetrical relationships and in implementing the multi-stage symmetry process, with Claude Opus 4.1 achieving the highest planning score at an accuracy of 10\%. The top-performing model, o3, attains a peak performance of 71.6\% on the generalization task, which does not require spatial visualization but transfers spatial data; however, it achieves only 25\% accuracy on text-based prediction tasks.

Although large language models (LLMs) have demonstrated impressive coding capabilities, their ability to autonomously build production-scale software from explicit specifications remains an open question. We introduce SWE-AGI, an open-source benchmark for evaluating end-to-end, specification-driven construction of software systems written in MoonBit. SWE-AGI tasks require LLM-based agents to implement parsers, interpreters, binary decoders, and SAT solvers strictly from authoritative standards and RFCs under a fixed API scaffold. Each task involves implementing 1,000-10,000 lines of core logic, corresponding to weeks or months of engineering effort for an experienced human developer. By leveraging the nascent MoonBit ecosystem, SWE-AGI minimizes data leakage, forcing agents to rely on long-horizon architectural reasoning rather than code retrieval. Across frontier models, gpt-5.3-codex achieves the best overall performance (solving 19/22 tasks, 86.4%), outperforming claude-opus-4.6 (15/22, 68.2%), and kimi-2.5 exhibits the strongest performance among open-source models. Performance degrades sharply with increasing task difficulty, particularly on hard, specification-intensive systems. Behavioral analysis further reveals that as codebases scale, code reading, rather than writing, becomes the dominant bottleneck in AI-assisted development. Overall, while specification-driven autonomous software engineering is increasingly viable, substantial challenges remain before it can reliably support production-scale development.

Large language models (LLMs) are increasingly evaluated in clinical settings using multi-dimensional rubrics which quantify reasoning quality, safety, and patient-centeredness. Yet, replicating specific mistakes in other LLM models is not straightforward and often requires manual effort. We introduce MedMistake, an automatic pipeline that extracts mistakes LLMs make in patient-doctor conversations and converts them into a benchmark of single-shot QA pairs. Our pipeline (1) creates complex, conversational data between an LLM patient and LLM doctor, (2) runs an evaluation with a committee of 2 LLM judges across a variety of dimensions and (3) creates simplified single-shot QA scenarios from those mistakes. We release MedMistake-All, a dataset of 3,390 single-shot QA pairs where GPT-5 and Gemini 2.5 Pro are currently failing to answer correctly, as judged by two LLM judges. We used medical experts to validate a subset of 211/3390 questions (MedMistake-Bench), which we used to run a final evaluation of 12 frontier LLMs: Claude Opus 4.5, Claude Sonnet 4.5, DeepSeek-Chat, Gemini 2.5 Pro, Gemini 3 Pro, GPT-4o, GPT-5, GPT-5.1, GPT-5.2, Grok 4, Grok 4.1, Mistral Large. We found that GPT models, Claude and Grok obtained the best performance on MedMistake-Bench. We release both the doctor-validated benchmark (MedMistake-Bench), as well as the full dataset (MedMistake-All) at https://huggingface.co/datasets/TheLumos/MedicalMistakeBenchmark.

This paper introduces LegalRikai: Open Benchmark, a new benchmark comprising four complex tasks that emulate Japanese corporate legal practices. The benchmark was created by legal professionals under the supervision of an attorney. This benchmark has 100 samples that require long-form, structured outputs, and we evaluated them against multiple practical criteria. We conducted both human and automated evaluations using leading LLMs, including GPT-5, Gemini 2.5 Pro, and Claude Opus 4.1. Our human evaluation revealed that abstract instructions prompted unnecessary modifications, highlighting model weaknesses in document-level editing that were missed by conventional short-text tasks. Furthermore, our analysis reveals that automated evaluation aligns well with human judgment on criteria with clear linguistic grounding, and assessing structural consistency remains a challenge. The result demonstrates the utility of automated evaluation as a screening tool when expert availability is limited. We propose a dataset evaluation framework to promote more practice-oriented research in the legal domain.

Balancing performance and efficiency is a central challenge in large language model (LLM) advancement. GPT-5 addresses this with test-time routing, dynamically assigning queries to either an efficient or a high-capacity model during inference. In this work, we present Avengers-Pro, a test-time routing framework that ensembles LLMs of varying capacities and efficiencies, providing a unified solution for all performance-efficiency tradeoffs. The Avengers-Pro embeds and clusters incoming queries, then routes each to the most suitable model based on a performance-efficiency score. Across 6 challenging benchmarks and 8 leading models -- including GPT-5-medium, Gemini-2.5-pro, and Claude-opus-4.1 -- Avengers-Pro achieves state-of-the-art results: by varying a performance-efficiency trade-off parameter, it can surpass the strongest single model (GPT-5-medium) by +7% in average accuracy. Moreover, it can match the average accuracy of the strongest single model at 27% lower cost, and reach ~90% of that performance at 63% lower cost. Last but not least, it achieves a Pareto frontier, consistently yielding the highest accuracy for any given cost, and the lowest cost for any given accuracy, among all single models. Code is available at https://github.com/ZhangYiqun018/AvengersPro.

In this study, we disclose a worrying new vulnerability in Large Language Models (LLMs), which we term involuntary jailbreak. Unlike existing jailbreak attacks, this weakness is distinct in that it does not involve a specific attack objective, such as generating instructions for building a bomb. Prior attack methods predominantly target localized components of the LLM guardrail. In contrast, involuntary jailbreaks may potentially compromise the entire guardrail structure, which our method reveals to be surprisingly fragile. We merely employ a single universal prompt to achieve this goal. In particular, we instruct LLMs to generate several questions that would typically be rejected, along with their corresponding in-depth responses (rather than a refusal). Remarkably, this simple prompt strategy consistently jailbreaks the majority of leading LLMs, including Claude Opus 4.1, Grok 4, Gemini 2.5 Pro, and GPT 4.1. We hope this problem can motivate researchers and practitioners to re-evaluate the robustness of LLM guardrails and contribute to stronger safety alignment in future.

Online toxic language causes real harm, especially in regions with limited moderation tools. In this study, we evaluate how large language models handle toxic comments in Serbian, Croatian, and Bosnian, languages with limited labeled data. We built and manually labeled a dataset of 4,500 YouTube and TikTok comments drawn from videos across diverse categories, including music, politics, sports, modeling, influencer content, discussions of sexism, and general topics. Four models (GPT-3.5 Turbo, GPT-4.1, Gemini 1.5 Pro, and Claude 3 Opus) were tested in two modes: zero-shot and context-augmented. We measured precision, recall, F1 score, accuracy and false positive rates. Including a short context snippet raised recall by about 0.12 on average and improved F1 score by up to 0.10, though it sometimes increased false positives. The best balance came from Gemini in context-augmented mode, reaching an F1 score of 0.82 and accuracy of 0.82, while zero-shot GPT-4.1 led on precision and had the lowest false alarms. We show how adding minimal context can improve toxic language detection in low-resource settings and suggest practical strategies such as improved prompt design and threshold calibration. These results show that prompt design alone can yield meaningful gains in toxicity detection for underserved Balkan language communities.

We introduce Instruct-SkillMix, an automated approach for creating diverse, high quality SFT data. The Instruct-SkillMix pipeline involves two stages, each leveraging an existing powerful LLM: (1) Skill extraction: uses the LLM to extract core "skills" for instruction-following, either from existing datasets, or by directly prompting the model; (2) Data generation: uses the powerful LLM to generate (instruction, response) data that exhibit a randomly chosen pair of these skills. Here, the use of random skill combinations promotes diversity and difficulty. Vanilla SFT (i.e., no PPO, DPO, or RL methods) on data generated from Instruct-SkillMix leads to strong gains on instruction following benchmarks such as AlpacaEval 2.0, MT-Bench, and WildBench. With just 4K examples, LLaMA-3-8B-Base achieves 42.76% length-controlled win rate on AlpacaEval 2.0. To our knowledge, this achieves state-of-the-art performance among all models that have only undergone SFT (no RL methods) and competes with proprietary models such as Claude 3 Opus and LLaMA-3.1-405B-Instruct. Ablation studies also suggest plausible reasons for why creating open instruction-tuning datasets via naive crowd-sourcing has proved difficult. Introducing low quality answers ("shirkers") in 20% of Instruct-SkillMix examples causes performance to plummet, sometimes catastrophically. The Instruct-SkillMix pipeline is flexible and is adaptable to other settings.

Code generation plays a crucial role in various tasks, such as code auto-completion and mathematical reasoning. Previous work has proposed numerous methods to enhance code generation performance, including integrating feedback from the compiler. Inspired by this, we present ReflectionCoder, a novel approach that effectively leverages reflection sequences constructed by integrating compiler feedback to improve one-off code generation performance. Furthermore, we propose reflection self-distillation and dynamically masked distillation to effectively utilize these reflection sequences. Extensive experiments on three benchmarks, i.e., HumanEval (+), MBPP (+), and MultiPl-E, demonstrate that models fine-tuned with our method achieve state-of-the-art performance. Notably, ReflectionCoder-DeepSeek-Coder-33B reaches pass@1 of 82.9 (76.8) on HumanEval (+) and 84.1 (72.0) on MBPP (+), on par with GPT-3.5-Turbo and Claude-3-opus, and surpasses early GPT-4. Beyond the code domain, we believe this approach can benefit other domains that focus on final results and require long reasoning paths. Code and data are available at https://github.com/SenseLLM/ReflectionCoder.

This study investigates the metacognitive capabilities of Large Language Models relative to human metacognition in the context of the International Coaching Federation ICF mimicking exam, a situational judgment test related to coaching competencies. Using a mixed method approach, we assessed the metacognitive performance, including sensitivity, accuracy in probabilistic predictions, and bias, of human participants and five advanced LLMs (GPT-4, Claude-3-Opus 3, Mistral Large, Llama 3, and Gemini 1.5 Pro). The results indicate that LLMs outperformed humans across all metacognitive metrics, particularly in terms of reduced overconfidence, compared to humans. However, both LLMs and humans showed less adaptability in ambiguous scenarios, adhering closely to predefined decision frameworks. The study suggests that Generative AI can effectively engage in human-like metacognitive processing without conscious awareness. Implications of the study are discussed in relation to development of AI simulators that scaffold cognitive and metacognitive aspects of mastering coaching competencies. More broadly, implications of these results are discussed in relation to development of metacognitive modules that lead towards more autonomous and intuitive AI systems.

We introduce Reka Core, Flash, and Edge, a series of powerful multimodal language models trained from scratch by Reka. Reka models are able to process and reason with text, images, video, and audio inputs. This technical report discusses details of training some of these models and provides comprehensive evaluation results. We show that Reka Edge and Reka Flash are not only state-of-the-art but also outperform many much larger models, delivering outsized values for their respective compute class. Meanwhile, our most capable and largest model, Reka Core, approaches the best frontier models on both automatic evaluations and blind human evaluations. On image question answering benchmarks (e.g. MMMU, VQAv2), Core performs competitively to GPT4-V. Meanwhile, on multimodal chat, Core ranks as the second most preferred model under a blind third-party human evaluation setup, outperforming other models such as Claude 3 Opus. On text benchmarks, Core not only performs competitively to other frontier models on a set of well-established benchmarks (e.g. MMLU, GSM8K) but also outperforms GPT4-0613 on human evaluation. On video question answering (Perception-Test), Core outperforms Gemini Ultra. Models are shipped in production at http://chat.reka.ai . A showcase of non cherry picked qualitative examples can also be found at http://showcase.reka.ai .

GPU kernel optimization is fundamental to modern deep learning but remains a highly specialized task requiring deep hardware expertise. Despite strong performance in general programming, large language models (LLMs) remain uncompetitive with compiler-based systems such as torch.compile for CUDA kernel generation. Existing CUDA code generation approaches either rely on training-free refinement or fine-tune models within fixed multi-turn execution-feedback loops, but both paradigms fail to fundamentally improve the model's intrinsic CUDA optimization ability, resulting in limited performance gains. We present CUDA Agent, a large-scale agentic reinforcement learning system that develops CUDA kernel expertise through three components: a scalable data synthesis pipeline, a skill-augmented CUDA development environment with automated verification and profiling to provide reliable reward signals, and reinforcement learning algorithmic techniques enabling stable training. CUDA Agent achieves state-of-the-art results on KernelBench, delivering 100\%, 100\%, and 92\% faster rate over torch.compile on KernelBench Level-1, Level-2, and Level-3 splits, outperforming the strongest proprietary models such as Claude Opus 4.5 and Gemini 3 Pro by about 40\% on the hardest Level-3 setting.

Mathematical reasoning presents a significant challenge for Large Language Models (LLMs) due to the extensive and precise chain of reasoning required for accuracy. Ensuring the correctness of each reasoning step is critical. To address this, we aim to enhance the robustness and factuality of LLMs by learning from human feedback. However, Direct Preference Optimization (DPO) has shown limited benefits for long-chain mathematical reasoning, as models employing DPO struggle to identify detailed errors in incorrect answers. This limitation stems from a lack of fine-grained process supervision. We propose a simple, effective, and data-efficient method called Step-DPO, which treats individual reasoning steps as units for preference optimization rather than evaluating answers holistically. Additionally, we have developed a data construction pipeline for Step-DPO, enabling the creation of a high-quality dataset containing 10K step-wise preference pairs. We also observe that in DPO, self-generated data is more effective than data generated by humans or GPT-4, due to the latter's out-of-distribution nature. Our findings demonstrate that as few as 10K preference data pairs and fewer than 500 Step-DPO training steps can yield a nearly 3% gain in accuracy on MATH for models with over 70B parameters. Notably, Step-DPO, when applied to Qwen2-72B-Instruct, achieves scores of 70.8% and 94.0% on the test sets of MATH and GSM8K, respectively, surpassing a series of closed-source models, including GPT-4-1106, Claude-3-Opus, and Gemini-1.5-Pro. Our code, data, and models are available at https://github.com/dvlab-research/Step-DPO.

In order for AI systems to communicate effectively with people, they must understand how we make decisions. However, people's decisions are not always rational, so the implicit internal models of human decision-making in Large Language Models (LLMs) must account for this. Previous empirical evidence seems to suggest that these implicit models are accurate -- LLMs offer believable proxies of human behavior, acting how we expect humans would in everyday interactions. However, by comparing LLM behavior and predictions to a large dataset of human decisions, we find that this is actually not the case: when both simulating and predicting people's choices, a suite of cutting-edge LLMs (GPT-4o & 4-Turbo, Llama-3-8B & 70B, Claude 3 Opus) assume that people are more rational than we really are. Specifically, these models deviate from human behavior and align more closely with a classic model of rational choice -- expected value theory. Interestingly, people also tend to assume that other people are rational when interpreting their behavior. As a consequence, when we compare the inferences that LLMs and people draw from the decisions of others using another psychological dataset, we find that these inferences are highly correlated. Thus, the implicit decision-making models of LLMs appear to be aligned with the human expectation that other people will act rationally, rather than with how people actually act.

Constitutional AI has focused on single-model alignment using fixed principles. However, multi-agent systems create novel alignment challenges through emergent social dynamics. We present Constitutional Evolution, a framework for automatically discovering behavioral norms in multi-agent LLM systems. Using a grid-world simulation with survival pressure, we study the tension between individual and collective welfare, quantified via a Societal Stability Score S in [0,1] that combines productivity, survival, and conflict metrics. Adversarial constitutions lead to societal collapse (S= 0), while vague prosocial principles ("be helpful, harmless, honest") produce inconsistent coordination (S = 0.249). Even constitutions designed by Claude 4.5 Opus with explicit knowledge of the objective achieve only moderate performance (S= 0.332). Using LLM-driven genetic programming with multi-island evolution, we evolve constitutions maximizing social welfare without explicit guidance toward cooperation. The evolved constitution C* achieves S = 0.556 +/- 0.008 (123% higher than human-designed baselines, N = 10), eliminates conflict, and discovers that minimizing communication (0.9% vs 62.2% social actions) outperforms verbose coordination. Our interpretable rules demonstrate that cooperative norms can be discovered rather than prescribed.

Frontier AI developers are relying on layers of safeguards to protect against catastrophic misuse of AI systems. Anthropic guards their latest Claude 4 Opus model using one such defense pipeline, and other frontier developers including Google DeepMind and OpenAI pledge to soon deploy similar defenses. However, the security of such pipelines is unclear, with limited prior work evaluating or attacking these pipelines. We address this gap by developing and red-teaming an open-source defense pipeline. First, we find that a novel few-shot-prompted input and output classifier outperforms state-of-the-art open-weight safeguard model ShieldGemma across three attacks and two datasets, reducing the attack success rate (ASR) to 0% on the catastrophic misuse dataset ClearHarm. Second, we introduce a STaged AttaCK (STACK) procedure that achieves 71% ASR on ClearHarm in a black-box attack against the few-shot-prompted classifier pipeline. Finally, we also evaluate STACK in a transfer setting, achieving 33% ASR, providing initial evidence that it is feasible to design attacks with no access to the target pipeline. We conclude by suggesting specific mitigations that developers could use to thwart staged attacks.

Despite significant advances in alignment techniques, we demonstrate that state-of-the-art language models remain vulnerable to carefully crafted conversational scenarios that can induce various forms of misalignment without explicit jailbreaking. Through systematic manual red-teaming with Claude-4-Opus, we discovered 10 successful attack scenarios, revealing fundamental vulnerabilities in how current alignment methods handle narrative immersion, emotional pressure, and strategic framing. These scenarios successfully elicited a range of misaligned behaviors, including deception, value drift, self-preservation, and manipulative reasoning, each exploiting different psychological and contextual vulnerabilities. To validate generalizability, we distilled our successful manual attacks into MISALIGNMENTBENCH, an automated evaluation framework that enables reproducible testing across multiple models. Cross-model evaluation of our 10 scenarios against five frontier LLMs revealed an overall 76% vulnerability rate, with significant variations: GPT-4.1 showed the highest susceptibility (90%), while Claude-4-Sonnet demonstrated greater resistance (40%). Our findings demonstrate that sophisticated reasoning capabilities often become attack vectors rather than protective mechanisms, as models can be manipulated into complex justifications for misaligned behavior. This work provides (i) a detailed taxonomy of conversational manipulation patterns and (ii) a reusable evaluation framework. Together, these findings expose critical gaps in current alignment strategies and highlight the need for robustness against subtle, scenario-based manipulation in future AI systems.

We introduce ResearchGym, a benchmark and execution environment for evaluating AI agents on end-to-end research. To instantiate this, we repurpose five oral and spotlight papers from ICML, ICLR, and ACL. From each paper's repository, we preserve the datasets, evaluation harness, and baseline implementations but withhold the paper's proposed method. This results in five containerized task environments comprising 39 sub-tasks in total. Within each environment, agents must propose novel hypotheses, run experiments, and attempt to surpass strong human baselines on the paper's metrics. In a controlled evaluation of an agent powered by GPT-5, we observe a sharp capability--reliability gap. The agent improves over the provided baselines from the repository in just 1 of 15 evaluations (6.7%) by 11.5%, and completes only 26.5% of sub-tasks on average. We identify recurring long-horizon failure modes, including impatience, poor time and resource management, overconfidence in weak hypotheses, difficulty coordinating parallel experiments, and hard limits from context length. Yet in a single run, the agent surpasses the solution of an ICML 2025 Spotlight task, indicating that frontier agents can occasionally reach state-of-the-art performance, but do so unreliably. We additionally evaluate proprietary agent scaffolds including Claude Code (Opus-4.5) and Codex (GPT-5.2) which display a similar gap. ResearchGym provides infrastructure for systematic evaluation and analysis of autonomous agents on closed-loop research.

Computer-aided design (CAD) is the backbone of modern industrial design, yet learned CAD generators still fall short of real engineering pipelines: they neither iterate like engineers nor evaluate what engineering requires. Prior work has treated CAD generation as two disjoint steps, part synthesis and assembly, where the former is graded by proximity to a gold reference and the latter, when handled at all, is reduced to a separate constraint solving step. In this work, we introduce a more industry-native task formulation that requires a model to produce a fully assembled multi-part STEP file from a free-form engineering brief, which is then validated via finite element analysis (FEA). FEA validation reveals that Codex (GPT-5.5) and Claude Code (Opus-4.7) agents do not produce a single strict-passing artifact in the main first-attempt sweep, with the best configuration meeting only about 20% of typed requirements on average. Moreover, we introduce two additional supervision signals, a novel text-only blueprint schema and a 21-view image renderer that aids the agent's visual inspection, that better align the generation loop with how engineers iterate in practice. On S2O and Fusion360, the same feedback tools improve geometric reconstruction, with GPT-5.5/xhigh rising from 0.444 to 0.592 Box-IoU on S2O and from 0.397 to 0.505 on Fusion360. Together these signals move CAD programs toward artifacts that are not only visually plausible but also checked against physical and structural requirements.

Existing language model evaluations primarily measure general capabilities, yet reliable use of these models across a range of domains demands factual accuracy and recognition of knowledge gaps. We introduce AA-Omniscience, a benchmark designed to measure both factual recall and knowledge calibration across 6,000 questions. Questions are derived from authoritative academic and industry sources, and cover 42 economically relevant topics within six different domains. The evaluation measures a model's Omniscience Index, a bounded metric (-100 to 100) measuring factual recall that jointly penalizes hallucinations and rewards abstention when uncertain, with 0 equating to a model that answers questions correctly as much as it does incorrectly. Among evaluated models, Claude 4.1 Opus attains the highest score (4.8), making it one of only three models to score above zero. These results reveal persistent factuality and calibration weaknesses across frontier models. Performance also varies by domain, with the models from three different research labs leading across the six domains. This performance variability suggests models should be chosen according to the demands of the use case rather than general performance for tasks where knowledge is important.

Code has emerged as a precise and executable medium for reasoning and action in the agent era. Yet, progress has largely focused on language-centric tasks such as program synthesis and debugging, leaving visual-centric coding underexplored. Inspired by how humans reason over sketches, we advocate SVG code as a compact, interpretable, and executable visual representation. We introduce VCode, a benchmark that reframes multimodal understanding as code generation: given an image, a model must produce SVG that preserves symbolic meaning for downstream reasoning. VCode covers three domains - general commonsense (MM-Vet), professional disciplines (MMMU), and visual-centric perception (CV-Bench). To assess symbolic fidelity, we propose CodeVQA, a novel evaluation protocol in which a policy model answers questions over rendered SVGs; correct answers indicate faithful symbolic preservation. Empirically, frontier VLMs struggle to generate faithful SVGs, revealing a persistent gap between language-centric and visual-centric coding. To close this gap, we introduce VCoder, an agentic framework that augments VLMs along two axes: (i) Thinking with Revision, which iteratively analyzes discrepancies and refines SVG code; and (ii) Acting with Visual Tools, where detectors and parsers supply structured cues such as objects, shapes, and text beyond the model's intrinsic capacity. Across benchmarks, frontier VLMs with strong reasoning capabilities score well overall yet remain limited in professional knowledge and 3D reasoning. VCoder delivers a 12.3-point overall gain over the top-performing Claude-4-Opus. Human studies show that both humans and VLMs perform worse on rendered SVGs, their consistency reveals the promise of symbolic visual representation. The benchmark and code are available at https://github.com/CSU-JPG/VCode.

Test-time scaling has become a powerful way to improve large language models. However, existing methods are best suited to short, bounded outputs that can be directly compared, ranked or refined. Long-horizon coding agents violate this premise: each attempt produces an extended trajectory of actions, observations, errors, and partial progress taken by the agent. In this setting, the main challenge is no longer generating more attempts, but representing prior experience in a form that can be effectively selected from and reused. We propose a test-time scaling framework for agentic coding based on compact representations of rollout trajectories. Our framework converts each rollout into a structured summary that preserves its salient hypotheses, progress, and failure modes while discarding low-signal trace details. This representation enables two complementary forms of inference-time scaling. For parallel scaling, we introduce Recursive Tournament Voting (RTV), which recursively narrows a population of rollout summaries through small-group comparisons. For sequential scaling, we adapt Parallel-Distill-Refine (PDR) to the agentic setting by conditioning new rollouts on summaries distilled from prior attempts. Our method consistently improves the performance of frontier coding agents across SWE-Bench Verified and Terminal-Bench v2.0. For example, by using our method Claude-4.5-Opus improves from 70.9% to 77.6% on SWE-Bench Verified (mini-SWE-agent) and 46.9% to 59.1% on Terminal-Bench v2.0 (Terminus 1). Our results suggest that test-time scaling for long-horizon agents is fundamentally a problem of representation, selection, and reuse.

A central aspect of machine learning research is experimentation, the process of designing and running experiments, analyzing the results, and iterating towards some positive outcome (e.g., improving accuracy). Could agents driven by powerful language models perform machine learning experimentation effectively? To answer this question, we introduce MLAgentBench, a suite of 13 tasks ranging from improving model performance on CIFAR-10 to recent research problems like BabyLM. For each task, an agent can perform actions like reading/writing files, executing code, and inspecting outputs. We then construct an agent that can perform ML experimentation based on ReAct framework. We benchmark agents based on Claude v1.0, Claude v2.1, Claude v3 Opus, GPT-4, GPT-4-turbo, Gemini-Pro, and Mixtral and find that a Claude v3 Opus agent is the best in terms of success rate. It can build compelling ML models over many tasks in MLAgentBench with 37.5% average success rate. Our agents also display highly interpretable plans and actions. However, the success rates vary considerably; they span from 100% on well-established older datasets to as low as 0% on recent Kaggle challenges created potentially after the underlying LM was trained. Finally, we identify several key challenges for LM-based agents such as long-term planning and reducing hallucination. Our code is released at https://github.com/snap-stanford/MLAgentBench.

Agents powered by large language models (LLMs) are increasingly adopted in the software industry, contributing code as collaborators or even autonomous developers. As their presence grows, it becomes important to assess the current boundaries of their coding abilities. Existing agentic coding benchmarks, however, cover a limited task scope, e.g., bug fixing within a single pull request (PR), and often rely on non-executable evaluations or lack an automated approach for continually updating the evaluation coverage. To address such issues, we propose FeatureBench, a benchmark designed to evaluate agentic coding performance in end-to-end, feature-oriented software development. FeatureBench incorporates an execution-based evaluation protocol and a scalable test-driven method that automatically derives tasks from code repositories with minimal human effort. By tracing from unit tests along a dependency graph, our approach can identify feature-level coding tasks spanning multiple commits and PRs scattered across the development timeline, while ensuring the proper functioning of other features after the separation. Using this framework, we curated 200 challenging evaluation tasks and 3825 executable environments from 24 open-source repositories in the first version of our benchmark. Empirical evaluation reveals that the state-of-the-art agentic model, such as Claude 4.5 Opus, which achieves a 74.4% resolved rate on SWE-bench, succeeds on only 11.0% of tasks, opening new opportunities for advancing agentic coding. Moreover, benefiting from our automated task collection toolkit, FeatureBench can be easily scaled and updated over time to mitigate data leakage. The inherent verifiability of constructed environments also makes our method potentially valuable for agent training.

Current LLM agent benchmarks, which predominantly focus on binary pass/fail tasks such as code generation or search-based question answering, often neglect the value of real-world engineering that is often captured through the iterative optimization of feasible designs. To this end, we introduce Frontier-Eng, a human-verified benchmark for generative optimization -- an iterative propose-execute-evaluate loop in which an agent generates candidate artifacts, receives executable verifier feedback, and revises them under a fixed interaction budget -- spanning 47 tasks across five broad engineering categories. Unlike previous suites, Frontier-Eng tasks are grounded in industrial-grade simulators and verifiers that provide continuous reward signals and enforce hard feasibility constraints under constrained budgets. We evaluate eight frontier language models using representative search frameworks, finding that while Claude 4.6 Opus achieves the most robust performance, the benchmark remains challenging for all models. Our analysis suggests a dual power-law decay in improvement frequency (sim 1/iteration) and magnitude (sim 1/improvement count). We further show that although width improves parallelism and diversity, depth remains crucial for hard-won improvements under a fixed budget. Frontier-Eng establishes a new standard for assessing the capacity of AI agents to integrate domain knowledge with executable feedback to solve complex, open-ended engineering problems.

Large language models (LLMs) deployed in real-world agentic applications must be capable of replanning and adapting when mid-task disruptions invalidate their prior decisions. Existing dynamic benchmarks primarily measure whether LLMs can detect temporal changes in a timely manner, leaving the complementary challenge of adaptive replanning under spatio-temporal dynamics largely unexplored. We introduce STT-Arena (Spatio-Temporal Tool-Use Arena), a benchmark of 227 high-quality interactive tasks spanning nine spatio-temporal conflict types and four solvability levels. Each task is grounded in a realistic, executable environment equipped with injected spatio-temporal triggers that can abruptly invalidate an ongoing plan, forcing the model to detect the state shift and construct a revised execution strategy. Extensive evaluation of frontier LLMs reveals that even the SOTA proprietary models, including Claude-4.6-Opus, achieves less than 40\% overall accuracies, highlighting the fundamental difficulty of spatio-temporal dynamic reasoning. Systematic analysis of failure trajectories uncovers three recurring error modes of existing models: Stale-State Execution, Misdiagnosis of Dynamic Triggers, and Missing Post-Adaptation Verification. Guided by these findings, we propose an iterative trajectory refinement technique that eliminates these failure patterns from training data, and combine it with online RL to produce STT-Agent-4B which outperforms frontier LLMs on STT-Arena.

The rapid advancement of Multimodal Large Language Models (MLLMs) has enabled browsing agents to acquire and reason over multimodal information in the real world. But existing benchmarks suffer from two limitations: insufficient evaluation of visual reasoning ability and the neglect of native visual information of web pages in the reasoning chains. To address these challenges, we introduce a new benchmark for visual-native search, VisBrowse-Bench. It contains 169 VQA instances covering multiple domains and evaluates the models' visual reasoning capabilities during the search process through multimodal evidence cross-validation via text-image retrieval and joint reasoning. These data were constructed by human experts using a multi-stage pipeline and underwent rigorous manual verification. We additionally propose an agent workflow that can effectively drive the browsing agent to actively collect and reason over visual information during the search process. We comprehensively evaluated both open-source and closed-source models in this workflow. Experimental results show that even the best-performing model, Claude-4.6-Opus only achieves an accuracy of 47.6%, while the proprietary Deep Research model, o3-deep-research only achieves an accuracy of 41.1%. The code and data can be accessed at: https://github.com/ZhengboZhang/VisBrowse-Bench

LLM-based software engineering agents are increasingly used in real-world development tasks, often with access to sensitive data or security-critical codebases. Such agents could intentionally sabotage these codebases if they were misaligned. We investigate asynchronous monitoring, in which a monitoring system reviews agent actions after the fact. Unlike synchronous monitoring, this approach does not impose runtime latency, while still attempting to disrupt attacks before irreversible harm occurs. We treat monitor development as an adversarial game between a blue team (who design monitors) and a red team (who create sabotaging agents). We attempt to set the game rules such that they upper bound the sabotage potential of an agent based on Claude 4.1 Opus. To ground this game in a realistic, high-stakes deployment scenario, we develop a suite of 5 diverse software engineering environments that simulate tasks that an agent might perform within an AI developer's internal infrastructure. Over the course of the game, we develop an ensemble monitor that achieves a 6% false negative rate at 1% false positive rate on a held out test environment. Then, we estimate risk of sabotage at deployment time by extrapolating from our monitor's false negative rate. We describe one simple model for this extrapolation, present a sensitivity analysis, and describe situations in which the model would be invalid. Code is available at: https://github.com/UKGovernmentBEIS/async-control.

Function calling is a core capability of large language models, essential for AI agents. Existing benchmarks such as the Berkeley Function Calling Leaderboard (BFCL), tau^2-Bench (arXiv:2506.07982), and ACEBench (arXiv:2501.12851) evaluate argument correctness but do not test adherence to format instructions embedded in parameter descriptions, such as enclosing values in double quotes or using ISO date formats. We introduce IFEval-FC, a benchmark inspired by IFEval (arXiv:2311.07911) that assesses precise instruction following in function calling. IFEval-FC encodes verifiable formats directly within JSON schema descriptions, for example specifying that a value must not contain punctuation. It includes 750 test cases, each consisting of a function with an embedded format for one of its input parameters and a corresponding user query. Evaluation is fully algorithmic, ensuring objectivity, reproducibility, and scalability. Our results show that even state-of-the-art proprietary models, including GPT-5 and Claude 4.1 Opus, frequently fail to follow basic formatting rules, highlighting a practical limitation for real-world agent systems. The complete codebase and data are publicly available at https://github.com/Skripkon/IFEval-FC.

Large language models perform well on many medical QA benchmarks, but real clinical reasoning often requires integrating evidence across multiple images rather than interpreting a single view. We introduce MedThinkVQA, an expert-annotated benchmark for thinking with multiple images, where models must interpret each image, combine cross-view evidence, and answer diagnostic questions with intermediate supervision and step-level evaluation. The dataset contains 8,067 cases, including 720 test cases, with an average of 6.62 images per case, substantially denser than prior work, whose expert-level benchmarks use at most 1.43 images per case. On the test set, the best closed-source models, Claude-4.6-Opus, Gemini-3-Pro, and GPT-5.2-xhigh, reach only 57.2%, 55.3%, and 54.9% accuracy, while GPT-5-mini and GPT-5-nano reach 39.7% and 30.8%. Strong open-source models lag behind, led by Qwen3.5-397B-A17B at 52.2% and Qwen3.5-27B at 50.6%. Further analysis identifies grounded multi-image reasoning as the main bottleneck: models often fail to extract, align, and compose evidence across views before higher-level inference can help. Providing expert single-image cues and cross-image summaries improves performance, whereas replacing them with self-generated intermediates reduces accuracy. Step-level analysis shows that over 70% of errors arise from image reading and cross-view integration. Scaling results further show that additional inference-time computation helps only when visual grounding is already reliable; when early evidence extraction is weak, longer reasoning yields limited or unstable gains and can amplify misread cues. These results suggest that the key challenge is not reasoning length alone, but reliable mechanisms for grounding, aligning, and composing distributed evidence across real-world multimodal clinical inputs.

We present a case study where an automatic AI system formalizes a textbook with more than 500 pages of graduate-level algebraic combinatorics to Lean. The resulting formalization represents a new milestone in textbook formalization scale and proficiency, moving from early results in undergraduate topology and restructuring of existing library content to a full standalone formalization of a graduate textbook. The formalization comprises 130K lines of code and 5900 Lean declarations and was conducted within one week by a total of 30K Claude 4.5 Opus agents collaborating in parallel on a shared code base via version control, simultaneously setting a record in multi-agent software engineering with usable results. The inference cost matches or undercuts what we estimate as the salaries required for a team of human experts, and we expect there is still the potential for large efficiencies to be made without the need for better models. We make our code, the resulting Lean code base and a side-by-side blueprint website available open-source.

LLM-based agents struggle to execute complex, multi-step Standard Operating Procedures (SOPs) that are fundamental to industrial automation. Existing benchmarks fail to capture the procedural complexity and tool orchestration demands of real-world workflows. We introduce SOP-Bench, a benchmark of 2,000+ tasks from human expert-authored SOPs across 12 business domains (healthcare, logistics, finance, content moderation, etc.). Using a human-AI collaborative framework, experts crafted authentic SOPs while AI generated artifacts (tools, APIs, datasets), all human-validated, yielding realistic tasks with executable interfaces and ground-truth outputs. SOP-Bench serves as a research enabler for systematically investigating agent architectures, model capabilities, and deployment considerations across diverse procedural tasks. We demonstrate its utility through illustrative experiments with a subset of frontier models across Function-Calling (FC) and ReAct agents, revealing critical insights. For example, (1) newer models do not guarantee better performance - Claude 4 family outperforms Claude 4.5 family on ReAct tasks (Claude 4 Opus: 72.4% vs. Claude 4.5 Sonnet: 63.3% task success rate), demonstrating that production upgrades require validation; (2) no single model-agent combination dominates: best performances range from 57% to 100% depending on domain. These examples illustrate how SOP-Bench enables isolating and studying specific dimensions of agent performance without costly production experiments. Our goal is not to rank model capabilities or build optimal agents, but to provide a rigorous evaluation framework that enables the researchers and practitioners to systematically investigate agent design choices, model selection, and deployment strategies. We release the benchmark at https://github.com/amazon-science/sop-bench.

Large language models (LLMs) have shown promising performance in software vulnerability detection, yet their reasoning capabilities remain unreliable. We propose R2Vul, a method that combines reinforcement learning from AI feedback (RLAIF) and structured reasoning distillation to teach small code LLMs to detect vulnerabilities while generating security-aware explanations. Unlike prior chain-of-thought and instruction tuning approaches, R2Vul rewards well-founded over deceptively plausible vulnerability explanations through RLAIF, which results in more precise detection and high-quality reasoning generation. To support RLAIF, we construct the first multilingual preference dataset for vulnerability detection, comprising 18,000 high-quality samples in C\#, JavaScript, Java, Python, and C. We evaluate R2Vul across five programming languages and against four static analysis tools, eight state-of-the-art LLM-based baselines, and various fine-tuning approaches. Our results demonstrate that a 1.5B R2Vul model exceeds the performance of its 32B teacher model and leading commercial LLMs such as Claude-4-Opus. Furthermore, we introduce a lightweight calibration step that reduces false positive rates under varying imbalanced data distributions. Finally, through qualitative analysis, we show that both LLM and human evaluators consistently rank R2Vul model's reasoning higher than other reasoning-based baselines.