Daily Papers

Large-language-model code generation has shifted from single-shot prompting to multi-agent orchestrations - analyst, coder, tester, and debugger pipelines - and is evaluated almost exclusively on functional correctness. Whether these architectures also affect the structural complexity of the code they produce, and which orchestration layers carry the cost, remains largely unexamined: prior work has documented prompt-level effects on code complexity, but the architecture-level question is open. We compare six widely-used multi-agent configurations (Basic, AC, ACT, Debugger, AC+Debugger, ACT+Debugger) under two models from the GPT-4o family across all 164 HumanEval tasks - 1,968 paired observations - using the five RADON complexity metrics (SLOC, cyclomatic complexity, and Halstead Volume, Difficulty, and Effort). We apply a paired non-parametric statistical pipeline (Friedman omnibus, Wilcoxon signed-rank post-hoc with Holm correction, Kendall's W and matched-pairs rank-biserial effect sizes) in both all-completions and passing-only conditions. The six architectures collapse into two indistinguishable complexity clusters separated by a 50-130% gap, the same partition in both models and under both conditions; among the architectural layers, the analyst-coder split inflates complexity, the runtime debugger does not - and on the analyst-coder background actively deflates it - and the tester re-inflates it. The heavy cluster's additional complexity buys no pass@1 advantage: the leanest architectures match or beat the heaviest on accuracy. Architectural elaboration in LLM code generation should therefore be justified by measured benefit on the dimensions that matter, not assumed.

Large Language Models (LLMs) have shown impressive performance across a wide array of tasks involving both structured and unstructured textual data. Recent results on various benchmarks for code generation, repair, or completion suggest that certain models have programming abilities comparable to or even surpass humans. In this work, we demonstrate that high performance on such benchmarks does not correlate to humans' innate ability to understand structural control flow in code. To this end, we extract solutions from the HumanEval benchmark, which the relevant models perform strongly on, and trace their execution path using function calls sampled from the respective test set. Using this dataset, we investigate the ability of seven state-of-the-art LLMs to match the execution trace and find that, despite their ability to generate semantically identical code, they possess limited ability to trace execution paths, especially for longer traces and specific control structures. We find that even the top-performing model, Gemini, can fully and correctly generate only 47% of HumanEval task traces. Additionally, we introduce a subset for three key structures not contained in HumanEval: Recursion, Parallel Processing, and Object-Oriented Programming, including concepts like Inheritance and Polymorphism. Besides OOP, we show that none of the investigated models achieve an accuracy over 5% on the relevant traces. Aggregating these specialized parts with HumanEval tasks, we present Benchmark CoCoNUT: Code Control Flow for Navigation Understanding and Testing, which measures a model's ability to trace execution of code upon relevant calls, including advanced structural components. We conclude that current LLMs need significant improvement to enhance code reasoning abilities. We hope our dataset helps researchers bridge this gap.

Self-Rewarding Language Models propose an architecture in which the Large Language Models(LLMs) both generates responses and evaluates its own outputs via LLM-as-a-Judge prompting, dynamically improving its generative capabilities through iterative Direct Preference Optimization (DPO). However, our analysis reveals a critical limitation in existing Self-Rewarding paradigms: the synchronized improvement of chosen and rejected responses progressively narrows the representational difference between contrasting samples, undermining effective preference learning. We propose Temporal Self-Rewarding Language Models that strategically coordinate past, present, and future model generations to sustain learning signals. Our dual-phase framework introduces: (1) Anchored Rejection - fixing rejected responses using the past initial model's outputs and (2) Future-Guided Chosen - dynamically curating chosen samples using next-generation model predictions. Extensive experiments across three model families (Llama, Qwen, Mistral) and different model sizes (Llama3B/8B/70B) demonstrate significant improvements when trained with our method compared to Self-Rewarding using same computation resources. For example, Llama3.1-8B reaches a 29.44 win rate on AlpacaEval 2.0 with our method, outperforming the Self-Rewarding baseline (19.69) by 9.75. Notably, our method also demonstrates superior out-of-distribution generalization across mathematical reasoning (GSM8K), knowledge-based QA (ARC, TruthfulQA), and code generation (HumanEval) tasks, even though we do not specifically collect such training data.

Quantum programs are typically developed using quantum Software Development Kits (SDKs). The rapid advancement of quantum computing necessitates new tools to streamline this development process, and one such tool could be Generative Artificial intelligence (GenAI). In this study, we introduce and use the Qiskit HumanEval dataset, a hand-curated collection of tasks designed to benchmark the ability of Large Language Models (LLMs) to produce quantum code using Qiskit - a quantum SDK. This dataset consists of more than 100 quantum computing tasks, each accompanied by a prompt, a canonical solution, a comprehensive test case, and a difficulty scale to evaluate the correctness of the generated solutions. We systematically assess the performance of a set of LLMs against the Qiskit HumanEval dataset's tasks and focus on the models ability in producing executable quantum code. Our findings not only demonstrate the feasibility of using LLMs for generating quantum code but also establish a new benchmark for ongoing advancements in the field and encourage further exploration and development of GenAI-driven tools for quantum code generation.

Large Language Models (LLMs) excel in stand-alone code tasks like HumanEval and MBPP, but struggle with handling entire code repositories. This challenge has prompted research on enhancing LLM-codebase interaction at a repository scale. Current solutions rely on similarity-based retrieval or manual tools and APIs, each with notable drawbacks. Similarity-based retrieval often has low recall in complex tasks, while manual tools and APIs are typically task-specific and require expert knowledge, reducing their generalizability across diverse code tasks and real-world applications. To mitigate these limitations, we introduce \framework, a system that integrates LLM agents with graph database interfaces extracted from code repositories. By leveraging the structural properties of graph databases and the flexibility of the graph query language, \framework enables the LLM agent to construct and execute queries, allowing for precise, code structure-aware context retrieval and code navigation. We assess \framework using three benchmarks: CrossCodeEval, SWE-bench, and EvoCodeBench. Additionally, we develop five real-world coding applications. With a unified graph database schema, \framework demonstrates competitive performance and potential in both academic and real-world environments, showcasing its versatility and efficacy in software engineering. Our application demo: https://github.com/modelscope/modelscope-agent/tree/master/apps/codexgraph_agent.

Understanding and reasoning over diagrams is a fundamental aspect of human intelligence. While Large Multimodal Models (LMMs) have demonstrated impressive capabilities across various tasks, existing benchmarks lack comprehensive evaluation of their diagram interpretation and reasoning abilities, particularly in coding contexts. We present HumanEval-V, a rigorous benchmark of human-annotated coding tasks that spans six task types and evaluates diverse visual reasoning capabilities. Each task features carefully crafted diagrams paired with function signatures and test cases, employing novel code generation tasks to thoroughly assess models' diagram comprehension. Through extensive experiments with 22 LMMs, we find that even top-performing models achieve modest success rates, with Claude 3.5 Sonnet reaching only 36.8% pass@1, highlighting substantial room for improvement. Our analysis reveals that current LMMs struggle with spatial transformations, topological relationships, and dynamic patterns that humans find intuitive. These findings provide valuable insights for advancing LMMs' visual reasoning abilities. We have open-sourced our code and benchmark at https://github.com/HumanEval-V/HumanEval-V-Benchmark.

We introduce self-invoking code generation, a new task designed to evaluate the progressive reasoning and problem-solving capabilities of LLMs. In this task, models are presented with a base problem and a related, more complex problem. They must solve the base problem and then utilize its solution to address the more complex one. This work features three key contributions. First, we propose a general recipe for generating more challenging versions of existing benchmarks, resulting in three new benchmarks: HumanEval Pro, MBPP Pro, and BigCodeBench-Lite Pro, specifically designed to assess LLMs on self-invoking code generation. Second, from the analysis of experimental results over twenty LLMs on our benchmarks, we have two important observations: (i) Most LLMs excel in traditional code generation benchmarks like HumanEval and MBPP, but their performance declines on self-invoking tasks. For example, o1-mini achieves 96.2% pass@1 on HumanEval but only 76.2% on HumanEval Pro. (ii) On self-invoking code generation task, the instruction-tuned models demonstrate only marginal improvements compared to the base models. Third, we disclose the types of failure modes that exist in our evaluation results. All these results underscore the need for further advancements in self-invoking code generation tasks and provide a new direction for future research on enhancing LLMs' code reasoning capabilities.

Large Language Models (LLMs) have shown remarkable capabilities in code generation tasks, yet they face significant limitations in handling complex, long-context programming challenges and demonstrating complex compositional reasoning abilities. This paper introduces a novel agentic framework for ``guided code generation'' that tries to address these limitations through a deliberately structured, fine-grained approach to code generation tasks. Our framework leverages LLMs' strengths as fuzzy searchers and approximate information retrievers while mitigating their weaknesses in long sequential reasoning and long-context understanding. Empirical evaluation using OpenAI's HumanEval benchmark with Meta's Llama 3.1 8B model (int4 precision) demonstrates a 23.79\% improvement in solution accuracy compared to direct one-shot generation. Our results indicate that structured, guided approaches to code generation can significantly enhance the practical utility of LLMs in software development while overcoming their inherent limitations in compositional reasoning and context handling.

Large language models (LLMs) have manifested strong ability to generate codes for productive activities. However, current benchmarks for code synthesis, such as HumanEval, MBPP, and DS-1000, are predominantly oriented towards introductory tasks on algorithm and data science, insufficiently satisfying challenging requirements prevalent in real-world coding. To fill this gap, we propose NaturalCodeBench (NCB), a challenging code benchmark designed to mirror the complexity and variety of scenarios in real coding tasks. NCB comprises 402 high-quality problems in Python and Java, meticulously selected from natural user queries from online coding services, covering 6 different domains. Noting the extraordinary difficulty in creating testing cases for real-world queries, we also introduce a semi-automated pipeline to enhance the efficiency of test case construction. Comparing with manual solutions, it achieves an efficiency increase of more than 4 times. Our systematic experiments on 39 LLMs find that performance gaps on NCB between models with close HumanEval scores could still be significant, indicating a lack of focus on practical code synthesis scenarios or over-specified optimization on HumanEval. On the other hand, even the best-performing GPT-4 is still far from satisfying on NCB. The evaluation toolkit and development set are available at https://github.com/THUDM/NaturalCodeBench.

Test-time scaling is a powerful approach to obtain better reasoning in large language models, but it becomes memory-bottlenecked during long-horizon decoding, as the KV-cache grows. KV-cache quantization can help improve this, but current methods are evaluated under prefill-like settings and errors behave differently under autoregressive decoding. We show that in the latter regime, quantization errors accumulate across timesteps, driven primarily by incorrect token scales. We introduce KVarN, a calibration-free KV-cache quantizer that applies a Hadamard rotation followed by a dual-scaling variance normalization across both axes of the K and V matrices. We find that this combination fixes outlying token-scale errors and substantially reduces error accumulation over existing baselines. KVarN establishes a new state-of-theart for KV-cache quantization on generative benchmarks, including MATH500, AIME24 and HumanEval, at 2-bit precision. A vLLM implementation of the KVarN method is available at https://github.com/huawei-csl/KVarN

Large pre-trained code generation models, such as OpenAI Codex, can generate syntax- and function-correct code, making the coding of programmers more productive and our pursuit of artificial general intelligence closer. In this paper, we introduce CodeGeeX, a multilingual model with 13 billion parameters for code generation. CodeGeeX is pre-trained on 850 billion tokens of 23 programming languages as of June 2022. Our extensive experiments suggest that CodeGeeX outperforms multilingual code models of similar scale for both the tasks of code generation and translation on HumanEval-X. Building upon HumanEval (Python only), we develop the HumanEval-X benchmark for evaluating multilingual models by hand-writing the solutions in C++, Java, JavaScript, and Go. In addition, we build CodeGeeX-based extensions on Visual Studio Code, JetBrains, and Cloud Studio, generating 4.7 billion tokens for tens of thousands of active users per week. Our user study demonstrates that CodeGeeX can help to increase coding efficiency for 83.4% of its users. Finally, CodeGeeX is publicly accessible and in Sep. 2022, we open-sourced its code, model weights (the version of 850B tokens), API, extensions, and HumanEval-X at https://github.com/THUDM/CodeGeeX.

Post-training, particularly reinforcement learning (RL) using self-play-generated data, has become a new learning paradigm for large language models (LLMs). However, scaling RL to develop a general reasoner remains a research challenge, as existing methods focus on task-specific reasoning without adequately addressing generalization across a broader range of tasks. Moreover, unlike traditional RL with limited action space, LLMs operate in an infinite space, making it crucial to search for valuable and diverse strategies to solve problems effectively. To address this, we propose searching within the action space on high-level abstract plans to enhance model generalization and introduce Critical Plan Step Learning (CPL), comprising: 1) searching on plan, using Monte Carlo Tree Search (MCTS) to explore diverse plan steps in multi-step reasoning tasks, and 2) learning critical plan steps through Step-level Advantage Preference Optimization (Step-APO), which integrates advantage estimates for step preference obtained via MCTS into Direct Preference Optimization (DPO). This combination helps the model effectively learn critical plan steps, enhancing both reasoning capabilities and generalization. Experimental results demonstrate that our method, trained exclusively on GSM8K and MATH, not only significantly improves performance on GSM8K (+10.5%) and MATH (+6.5%), but also enhances out-of-domain reasoning benchmarks, such as HumanEval (+12.2%), GPQA (+8.6%), ARC-C (+4.0%), MMLU-STEM (+2.2%), and BBH (+1.8%).

Language is not monolithic. While many benchmarks are used as proxies to systematically estimate Large Language Models' (LLM) performance in real-life tasks, they tend to ignore the nuances of within-language variation and thus fail to model the experience of speakers of minority dialects. Focusing on African American Vernacular English (AAVE), we present the first study on LLMs' fairness and robustness to a dialect in canonical reasoning tasks (algorithm, math, logic, and comprehensive reasoning). We hire AAVE speakers, including experts with computer science backgrounds, to rewrite seven popular benchmarks, such as HumanEval and GSM8K. The result of this effort is ReDial, a dialectal benchmark comprising 1.2K+ parallel query pairs in Standardized English and AAVE. We use ReDial to evaluate state-of-the-art LLMs, including GPT-4o/4/3.5-turbo, LLaMA-3.1/3, Mistral, and Phi-3. We find that, compared to Standardized English, almost all of these widely used models show significant brittleness and unfairness to queries in AAVE. Furthermore, AAVE queries can degrade performance more substantially than misspelled texts in Standardized English, even when LLMs are more familiar with the AAVE queries. Finally, asking models to rephrase questions in Standardized English does not close the performance gap but generally introduces higher costs. Overall, our findings indicate that LLMs provide unfair service to dialect users in complex reasoning tasks. Code can be found at https://github.com/fangru-lin/redial_dialect_robustness_fairness.git.

A fundamental skill among human developers is the ability to understand and reason about program execution. As an example, a programmer can mentally simulate code execution in natural language to debug and repair code (aka. rubber duck debugging). However, large language models (LLMs) of code are typically trained on the surface textual form of programs, thus may lack a semantic understanding of how programs execute at run-time. To address this issue, we propose NExT, a method to teach LLMs to inspect the execution traces of programs (variable states of executed lines) and reason about their run-time behavior through chain-of-thought (CoT) rationales. Specifically, NExT uses self-training to bootstrap a synthetic training set of execution-aware rationales that lead to correct task solutions (e.g., fixed programs) without laborious manual annotation. Experiments on program repair tasks based on MBPP and HumanEval demonstrate that NExT improves the fix rate of a PaLM 2 model, by 26.1% and 14.3% absolute, respectively, with significantly improved rationale quality as verified by automated metrics and human raters. Our model can also generalize to scenarios where program traces are absent at test-time.

Though LLMs are capable of generating plausible programs, it's challenging to interact with the LLMs further to revise the program, especially if the user's specific requirements are different from the initial proposal. In this paper, we introduce ANPL, an interactive programming system that ensures users can always refine the generated code towards their specific programmatic intents via structured decompositions. Borrowing the paradigm of sketching from program synthesis, an ANPL program consists of a set of input-outputs that it must satisfy, a ``sketch'' -- control/data flow expressed in precise code (e.g. Python), and ``holes'' -- sub-modules to be implemented by the LLM specified with natural language. The user revises an ANPL program by either modifying the sketch, changing the language used to describe the holes, or providing additional input-outputs to a particular hole, turning it into a sub-ANPL program that can be solved recursively. This workflow allows the users to offload programming burdens to the LLM as much as possible while retaining the ability to pinpoint and resolve bugs locally, without exposing the rest of the program to the LLM. We deploy ANPL on the Abstraction and Reasoning Corpus (ARC), a set of unique tasks that are challenging for state-of-the-art AI systems, showing it outperforms baseline programming systems that (a) without the ability to decompose tasks interactively and (b) without the guarantee that the modules can be correctly composed together. Additional evaluations on APPS, HumanEval, and real-world programming tasks have validated that the ANPL framework is applicable to multiple programming domains. We release the ANPL solutions to the ARC tasks as a dataset, providing insights into how humans decompose novel tasks programmatically. See our code at https://iprc-dip.github.io/ANPL/.

Large Language Models (LLMs) have shown promise in automated code generation but typically excel only in simpler tasks such as generating standalone code units. Real-world software development, however, often involves complex code repositories (named repo) with complex dependencies and extensive documentation. To fill this gap, our research pivots towards evaluating LLMs in a more realistic setting -- real-world repo-level code generation. We introduce CodeAgentBench, a manually curated benchmark for repo-level code generation. This benchmark comprises five high-quality Python projects, encompassing a total of 101 samples. We assess nine leading LLMs on repo-level tasks and observe a decline in their performance. To tackle this, we present CodeAgent, a novel LLM-based agent framework that employs external tools for effective repo-level code generation. CodeAgent integrates five programming tools, enabling interaction with software artifacts for information retrieval, code symbol navigation, and code testing. We implement four agent strategies to optimize these tools' usage. Our experiments on CodeAgentBench show that CodeAgent enhances LLM performance significantly, with improvements ranging from 18.1\% to 250\%. Further tests on the HumanEval benchmark confirm CodeAgent's adaptability and efficacy across various code generation tasks. Notably, CodeAgent outperforms commercial products like Github Copilot, showcasing superior accuracy and efficiency. These results demonstrate CodeAgent's robust capabilities in code generation, highlighting its potential for real-world repo-level coding challenges.

The critique capacity of Large Language Models (LLMs) is essential for reasoning abilities, which can provide necessary suggestions (e.g., detailed analysis and constructive feedback). Therefore, how to evaluate the critique capacity of LLMs has drawn great attention and several critique benchmarks have been proposed. However, existing critique benchmarks usually have the following limitations: (1). Focusing on diverse reasoning tasks in general domains and insufficient evaluation on code tasks (e.g., only covering code generation task), where the difficulty of queries is relatively easy (e.g., the code queries of CriticBench are from Humaneval and MBPP). (2). Lacking comprehensive evaluation from different dimensions. To address these limitations, we introduce a holistic code critique benchmark for LLMs called CodeCriticBench. Specifically, our CodeCriticBench includes two mainstream code tasks (i.e., code generation and code QA) with different difficulties. Besides, the evaluation protocols include basic critique evaluation and advanced critique evaluation for different characteristics, where fine-grained evaluation checklists are well-designed for advanced settings. Finally, we conduct extensive experimental results of existing LLMs, which show the effectiveness of CodeCriticBench.

Mixture-of-Experts (MoE) models scale more effectively than dense models due to sparse computation through expert routing, selectively activating only a small subset of expert modules. However, sparse computation challenges traditional training practices, as discrete expert routing hinders standard backpropagation and thus gradient-based optimization, which are the cornerstone of deep learning. To better pursue the scaling power of MoE, we introduce GRIN (GRadient-INformed MoE training), which incorporates sparse gradient estimation for expert routing and configures model parallelism to avoid token dropping. Applying GRIN to autoregressive language modeling, we develop a top-2 16times3.8B MoE model. Our model, with only 6.6B activated parameters, outperforms a 7B dense model and matches the performance of a 14B dense model trained on the same data. Extensive evaluations across diverse tasks demonstrate the potential of GRIN to significantly enhance MoE efficacy, achieving 79.4 on MMLU, 83.7 on HellaSwag, 74.4 on HumanEval, and 58.9 on MATH.

Code generation models have achieved impressive performance. However, they tend to be brittle as slight edits to a prompt could lead to very different generations; these robustness properties, critical for user experience when deployed in real-life applications, are not well understood. Most existing works on robustness in text or code tasks have focused on classification, while robustness in generation tasks is an uncharted area and to date there is no comprehensive benchmark for robustness in code generation. In this paper, we propose ReCode, a comprehensive robustness evaluation benchmark for code generation models. We customize over 30 transformations specifically for code on docstrings, function and variable names, code syntax, and code format. They are carefully designed to be natural in real-life coding practice, preserve the original semantic meaning, and thus provide multifaceted assessments of a model's robustness performance. With human annotators, we verified that over 90% of the perturbed prompts do not alter the semantic meaning of the original prompt. In addition, we define robustness metrics for code generation models considering the worst-case behavior under each type of perturbation, taking advantage of the fact that executing the generated code can serve as objective evaluation. We demonstrate ReCode on SOTA models using HumanEval, MBPP, as well as function completion tasks derived from them. Interesting observations include: better robustness for CodeGen over InCoder and GPT-J; models are most sensitive to syntax perturbations; more challenging robustness evaluation on MBPP over HumanEval.

Unlike autoregressive language models, which terminate variable-length generation upon predicting an End-of-Sequence (EoS) token, Diffusion Language Models (DLMs) operate over a fixed maximum-length context window for a predetermined number of denoising steps. However, this process is independent of the required response length, resulting in computational waste for the majority of short responses common in reasoning and chat tasks. To address this problem, we conjecture that the latent prompt representation contains sufficient information to estimate the required output length. We provide empirical evidence for this phenomenon and propose a zero-shot mechanism to dynamically crop the context window before generation begins, leading to fewer diffusion steps and substantial computational savings. We evaluate our approach on four benchmarks with diverse tasks -- GSM8K (reasoning), HumanEval (code generation), IfEval (instruction following), and LongFormQA (question answering) -- revealing massive efficiency gains at minimal performance impact. We report significant reductions in FLOPs across all tasks, with no statistically significant performance degradation, and significant performance improvements in 2 out of 4 tasks.

The code generation capabilities of Large Language Models (LLMs) have advanced applications like tool invocation and problem-solving. However, improving performance in code-related tasks remains challenging due to limited training data that is verifiable with accurate test cases. While Direct Preference Optimization (DPO) has shown promise, existing methods for generating test cases still face limitations. In this paper, we propose a novel approach that splits code snippets into smaller, granular blocks, creating more diverse DPO pairs from the same test cases. Additionally, we introduce the Abstract Syntax Tree (AST) splitting and curriculum training method to enhance the DPO training. Our approach demonstrates significant improvements in code generation tasks, as validated by experiments on benchmark datasets such as HumanEval (+), MBPP (+), APPS, LiveCodeBench, and BigCodeBench. Code and data are available at https://github.com/SenseLLM/StructureCoder.

While LLaDA2.0 showcased the scaling potential of 100B-level block-diffusion models and their inherent parallelization, the delicate equilibrium between decoding speed and generation quality has remained an elusive frontier. Today, we unveil LLaDA2.1, a paradigm shift designed to transcend this trade-off. By seamlessly weaving Token-to-Token (T2T) editing into the conventional Mask-to-Token (M2T) scheme, we introduce a joint, configurable threshold-decoding scheme. This structural innovation gives rise to two distinct personas: the Speedy Mode (S Mode), which audaciously lowers the M2T threshold to bypass traditional constraints while relying on T2T to refine the output; and the Quality Mode (Q Mode), which leans into conservative thresholds to secure superior benchmark performances with manageable efficiency degrade. Furthering this evolution, underpinned by an expansive context window, we implement the first large-scale Reinforcement Learning (RL) framework specifically tailored for dLLMs, anchored by specialized techniques for stable gradient estimation. This alignment not only sharpens reasoning precision but also elevates instruction-following fidelity, bridging the chasm between diffusion dynamics and complex human intent. We culminate this work by releasing LLaDA2.1-Mini (16B) and LLaDA2.1-Flash (100B). Across 33 rigorous benchmarks, LLaDA2.1 delivers strong task performance and lightning-fast decoding speed. Despite its 100B volume, on coding tasks it attains an astounding 892 TPS on HumanEval+, 801 TPS on BigCodeBench, and 663 TPS on LiveCodeBench.

Finetuning large language models (LLMs) on instructions leads to vast performance improvements on natural language tasks. We apply instruction tuning using code, leveraging the natural structure of Git commits, which pair code changes with human instructions. We compile CommitPack: 4 terabytes of Git commits across 350 programming languages. We benchmark CommitPack against other natural and synthetic code instructions (xP3x, Self-Instruct, OASST) on the 16B parameter StarCoder model, and achieve state-of-the-art performance among models not trained on OpenAI outputs, on the HumanEval Python benchmark (46.2% pass@1). We further introduce HumanEvalPack, expanding the HumanEval benchmark to a total of 3 coding tasks (Code Repair, Code Explanation, Code Synthesis) across 6 languages (Python, JavaScript, Java, Go, C++, Rust). Our models, OctoCoder and OctoGeeX, achieve the best performance across HumanEvalPack among all permissive models, demonstrating CommitPack's benefits in generalizing to a wider set of languages and natural coding tasks. Code, models and data are freely available at https://github.com/bigcode-project/octopack.

Large Language Models (LLMs) have already become quite proficient at solving simpler programming tasks like those in HumanEval or MBPP benchmarks. However, solving more complex and competitive programming tasks is still quite challenging for these models - possibly due to their tendency to generate solutions as monolithic code blocks instead of decomposing them into logical sub-tasks and sub-modules. On the other hand, experienced programmers instinctively write modularized code with abstraction for solving complex tasks, often reusing previously developed modules. To address this gap, we propose CodeChain, a novel framework for inference that elicits modularized code generation through a chain of self-revisions, each being guided by some representative sub-modules generated in previous iterations. Concretely, CodeChain first instructs the LLM to generate modularized codes through chain-of-thought prompting. Then it applies a chain of self-revisions by iterating the two steps: 1) extracting and clustering the generated sub-modules and selecting the cluster representatives as the more generic and re-usable implementations, and 2) augmenting the original chain-of-thought prompt with these selected module-implementations and instructing the LLM to re-generate new modularized solutions. We find that by naturally encouraging the LLM to reuse the previously developed and verified sub-modules, CodeChain can significantly boost both modularity as well as correctness of the generated solutions, achieving relative pass@1 improvements of 35% on APPS and 76% on CodeContests. It is shown to be effective on both OpenAI LLMs as well as open-sourced LLMs like WizardCoder. We also conduct comprehensive ablation studies with different methods of prompting, number of clusters, model sizes, program qualities, etc., to provide useful insights that underpin CodeChain's success.

LLM-powered coding agents are redefining how real-world software is developed. To drive the research towards better coding agents, we require challenging benchmarks that can rigorously evaluate the ability of such agents to perform various software engineering tasks. However, popular coding benchmarks such as HumanEval and SWE-Bench focus on narrowly scoped tasks such as competition programming and patch generation. In reality, software engineers have to handle a broader set of tasks for real-world software development. To address this gap, we propose OmniCode, a novel software engineering benchmark that contains a broader and more diverse set of task categories beyond code or patch generation. Overall, OmniCode contains 1794 tasks spanning three programming languages (Python, Java, and C++) and four key categories: bug fixing, test generation, code review fixing, and style fixing. In contrast to prior software engineering benchmarks, the tasks in OmniCode are (1) manually validated to eliminate ill-defined problems, and (2) synthetically crafted or recently curated to avoid data leakage issues, presenting a new framework for synthetically generating diverse software tasks from limited real-world data. We evaluate OmniCode with popular agent frameworks such as SWE-Agent and show that while they may perform well on bug fixing for Python, they fall short on tasks such as Test Generation and in languages such as C++ and Java. For instance, SWE-Agent achieves a maximum of 20.9% with DeepSeek-V3.1 on Java Test Generation tasks. OmniCode aims to serve as a robust benchmark and spur the development of agents that can perform well across different aspects of software development. Code and data are available at https://github.com/seal-research/OmniCode.

The landscape of software development has witnessed a paradigm shift with the advent of AI-powered assistants, exemplified by GitHub Copilot. However, existing solutions are not leveraging all the potential capabilities available in an IDE such as building, testing, executing code, git operations, etc. Therefore, they are constrained by their limited capabilities, primarily focusing on suggesting code snippets and file manipulation within a chat-based interface. To fill this gap, we present AutoDev, a fully automated AI-driven software development framework, designed for autonomous planning and execution of intricate software engineering tasks. AutoDev enables users to define complex software engineering objectives, which are assigned to AutoDev's autonomous AI Agents to achieve. These AI agents can perform diverse operations on a codebase, including file editing, retrieval, build processes, execution, testing, and git operations. They also have access to files, compiler output, build and testing logs, static analysis tools, and more. This enables the AI Agents to execute tasks in a fully automated manner with a comprehensive understanding of the contextual information required. Furthermore, AutoDev establishes a secure development environment by confining all operations within Docker containers. This framework incorporates guardrails to ensure user privacy and file security, allowing users to define specific permitted or restricted commands and operations within AutoDev. In our evaluation, we tested AutoDev on the HumanEval dataset, obtaining promising results with 91.5% and 87.8% of Pass@1 for code generation and test generation respectively, demonstrating its effectiveness in automating software engineering tasks while maintaining a secure and user-controlled development environment.

Reinforcement learning from human feedback (RLHF) is one of the key techniques that helps large language models (LLMs) to follow instructions and provide helpful and harmless responses. While direct policy optimization methods exist, state-of-the-art LLMs adopt RL-based methods (usually PPO) in RLHF to train the policy to generate good responses guided by a reward model learned from preference data. The main challenge of these methods is the inaccuracy of the intermediate reward model, especially in code generation tasks that require long and complex reasoning to score a response. We find that the reliability of the reward model varies across responses assigned with different rewards. This motivates us to filter the samples whose rewards may be unreliable to improve signal-to-noise ratio during policy learning, resulting in Policy Filtration for Proximal Policy Optimization (PF-PPO). To choose a proper policy filtration strategy for a given reward model, the coefficient of determination (R^2) between rewards and actual scores on filtered samples serves as a good metrics and helps us find several promising strategies. We provide extensive experiments to validate the effectiveness of PF-PPO in code generation tasks, and find that some variants of PF-PPO are highly effective and achieve new state-of-the-art performance across 7-billion-parameter models on HumanEval, MBPP, and a new and more challenging LeetCode Contest benchmark.

Frontier reasoning models have exhibited incredible capabilities across a wide array of disciplines, driven by posttraining large language models (LLMs) with reinforcement learning (RL). However, despite the widespread success of this paradigm, much of the literature has been devoted to disentangling truly novel behaviors that emerge during RL but are not present in the base models. In our work, we approach this question from a different angle, instead asking whether comparable reasoning capabilites can be elicited from base models at inference time by pure sampling, without any additional training. Inspired by Markov chain Monte Carlo (MCMC) techniques for sampling from sharpened distributions, we propose a simple iterative sampling algorithm leveraging the base models' own likelihoods. Over different base models, we show that our algorithm offers substantial boosts in reasoning that nearly match and even outperform those from RL on a wide variety of single-shot tasks, including MATH500, HumanEval, and GPQA. Moreover, our sampler avoids the collapse in diversity over multiple samples that is characteristic of RL-posttraining. Crucially, our method does not require training, curated datasets, or a verifier, suggesting broad applicability beyond easily verifiable domains.

This work studies how to adaptively recompute key-value (KV) caches for diffusion large language models (DLMs) to maximize prediction accuracy while minimizing decoding latency. Prior methods' decoders recompute QKV for all tokens at every denoising step and layer, despite KV states changing little across most steps, especially in shallow layers, leading to substantial redundancy. We make three observations: (1) distant {bf MASK} tokens primarily act as a length-bias and can be cached block-wise beyond the active prediction window; (2) KV dynamics increase with depth, suggesting that selective refresh starting from deeper layers is sufficient; and (3) the most-attended token exhibits the smallest KV drift, providing a conservative lower bound on cache change for other tokens. Building on these, we propose {bf Elastic-Cache}, a training-free, architecture-agnostic strategy that jointly decides {when} to refresh (via an attention-aware drift test on the most-attended token) and {where} to refresh (via a depth-aware schedule that recomputes from a chosen layer onward while reusing shallow-layer caches and off-window MASK caches). Unlike fixed-period schemes, Elastic-Cache performs adaptive, layer-aware cache updates for diffusion LLMs, reducing redundant computation and accelerating decoding with negligible loss in generation quality. Experiments on LLaDA-Instruct, LLaDA-1.5, and LLaDA-V across mathematical reasoning and code generation tasks demonstrate consistent speedups: 8.7times on GSM8K (256 tokens), 45.1times on longer sequences, and 4.8times on HumanEval, while consistently maintaining higher accuracy than the baseline. Our method achieves significantly higher throughput (6.8times on GSM8K) than existing confidence-based approaches while preserving generation quality, enabling practical deployment of diffusion LLMs.

This paper introduces long-context Granite code models that support effective context windows of up to 128K tokens. Our solution for scaling context length of Granite 3B/8B code models from 2K/4K to 128K consists of a light-weight continual pretraining by gradually increasing its RoPE base frequency with repository-level file packing and length-upsampled long-context data. Additionally, we also release instruction-tuned models with long-context support which are derived by further finetuning the long context base models on a mix of permissively licensed short and long-context instruction-response pairs. While comparing to the original short-context Granite code models, our long-context models achieve significant improvements on long-context tasks without any noticeable performance degradation on regular code completion benchmarks (e.g., HumanEval). We release all our long-context Granite code models under an Apache 2.0 license for both research and commercial use.

Code completion models have made significant progress in recent years, yet current popular evaluation datasets, such as HumanEval and MBPP, predominantly focus on code completion tasks within a single file. This over-simplified setting falls short of representing the real-world software development scenario where repositories span multiple files with numerous cross-file dependencies, and accessing and understanding cross-file context is often required to complete the code correctly. To fill in this gap, we propose CrossCodeEval, a diverse and multilingual code completion benchmark that necessitates an in-depth cross-file contextual understanding to complete the code accurately. CrossCodeEval is built on a diverse set of real-world, open-sourced, permissively-licensed repositories in four popular programming languages: Python, Java, TypeScript, and C#. To create examples that strictly require cross-file context for accurate completion, we propose a straightforward yet efficient static-analysis-based approach to pinpoint the use of cross-file context within the current file. Extensive experiments on state-of-the-art code language models like CodeGen and StarCoder demonstrate that CrossCodeEval is extremely challenging when the relevant cross-file context is absent, and we see clear improvements when adding these context into the prompt. However, despite such improvements, the pinnacle of performance remains notably unattained even with the highest-performing model, indicating that CrossCodeEval is also capable of assessing model's capability in leveraging extensive context to make better code completion. Finally, we benchmarked various methods in retrieving cross-file context, and show that CrossCodeEval can also be used to measure the capability of code retrievers.

Tokenization is an understudied and often neglected component of modern LLMs. Most published works use a single tokenizer for all experiments, often borrowed from another model, without performing ablations or analysis to optimize tokenization. Moreover, the tokenizer is generally kept unchanged when fine-tuning a base model. In this paper, we show that the size, pre-tokenization regular expression, and training data of a tokenizer can significantly impact the model's generation speed, effective context size, memory usage, and downstream performance. We train specialized Byte-Pair Encoding code tokenizers, and conduct extensive ablations on the impact of tokenizer design on the performance of LLMs for code generation tasks such as HumanEval and MBPP, and provide recommendations for tokenizer hyper-parameters selection and switching the tokenizer in a pre-trained LLM. We perform our experiments on models trained from scratch and from pre-trained models, verifying their applicability to a wide range of use-cases. We find that when fine-tuning on more than 50 billion tokens, we can specialize the tokenizer of a pre-trained LLM to obtain large gains in generation speed and effective context size.

Establishing fair and robust benchmarks is essential for evaluating intelligent code generation by large language models (LLMs). Our survey of 35 existing benchmarks uncovers three major imbalances: 85.7% focus on a single programming language; 94.3% target only function-level or statement-level tasks; and over 80% include fewer than ten test cases on average. To address these gaps, we propose MultiOOP, a multi-language object-oriented programming benchmark covering six popular languages (Python, PHP, C++, C#, Java, JavaScript) with 267 tasks per language. We design a translator that extends an existing single-language OOP benchmark and the pass@o metric to a multilingual setting. Moreover, we propose an automated framework for augmenting test cases to ensure the reliability of the evaluation results. We evaluate 14 mainstream LLMs under zero-shot prompting and report three key findings: 1) Substantial performance degradation: pass@1 scores on MultiOOP drop by up to 65.6 percentage points compared to function-level tasks (e.g., HumanEval). 2) Cross-language variability: GPT-4o mini achieves pass@1 of 48.06% in Python but only 0.12%-15.26% in other languages, indicating limited multilingual generalization. 3) Conceptual gaps: pass@o scores are consistently 1.1-19.2 points lower than pass@k, demonstrating that LLMs often generate executable code without fully capturing core OOP concepts. Our benchmark, metric extensions, and evaluation scripts will be publicly released to foster a more balanced and comprehensive assessment of LLMs in object-oriented code generation. Our code and data will be released at https://github.com/alphadl/OOP-eval and https://huggingface.co/datasets/codeai-dteam/MultiOOP respectively.

Differential Transformer has recently been proposed to improve performance in Transformer models by canceling out noise through a denoiser attention mechanism. In this work, we introduce DiffLoRA, a parameter-efficient adaptation of the differential attention mechanism, with low-rank adapters on both positive and negative attention terms. This approach retains the efficiency of LoRA while aiming to benefit from the performance gains of differential attention. We evaluate DiffLoRA across a broad range of NLP tasks, including general benchmarks, many-shot in-context learning, RAG, and long-context tests. We observe that, although DiffLoRA falls short of other parameter-efficient fine-tuning methods in most evaluation tasks, it shows interesting results in certain domains (+11 pts on LoRA for HumanEval). We analyze the attention patterns post-finetuning to identify the reasons for this behavior.

We introduce ChatGLM, an evolving family of large language models that we have been developing over time. This report primarily focuses on the GLM-4 language series, which includes GLM-4, GLM-4-Air, and GLM-4-9B. They represent our most capable models that are trained with all the insights and lessons gained from the preceding three generations of ChatGLM. To date, the GLM-4 models are pre-trained on ten trillions of tokens mostly in Chinese and English, along with a small set of corpus from 24 languages, and aligned primarily for Chinese and English usage. The high-quality alignment is achieved via a multi-stage post-training process, which involves supervised fine-tuning and learning from human feedback. Evaluations show that GLM-4 1) closely rivals or outperforms GPT-4 in terms of general metrics such as MMLU, GSM8K, MATH, BBH, GPQA, and HumanEval, 2) gets close to GPT-4-Turbo in instruction following as measured by IFEval, 3) matches GPT-4 Turbo (128K) and Claude 3 for long context tasks, and 4) outperforms GPT-4 in Chinese alignments as measured by AlignBench. The GLM-4 All Tools model is further aligned to understand user intent and autonomously decide when and which tool(s) touse -- including web browser, Python interpreter, text-to-image model, and user-defined functions -- to effectively complete complex tasks. In practical applications, it matches and even surpasses GPT-4 All Tools in tasks like accessing online information via web browsing and solving math problems using Python interpreter. Over the course, we have open-sourced a series of models, including ChatGLM-6B (three generations), GLM-4-9B (128K, 1M), GLM-4V-9B, WebGLM, and CodeGeeX, attracting over 10 million downloads on Hugging face in the year 2023 alone. The open models can be accessed through https://github.com/THUDM and https://huggingface.co/THUDM.

Instruction tuning plays a crucial role in shaping the outputs of language models (LMs) to desired styles. In this work, we propose a simple yet effective method, Instruction Modelling (IM), which trains LMs by applying a loss function to the instruction and prompt part rather than solely to the output part. Through experiments across 21 diverse benchmarks, we show that, in many scenarios, IM can effectively improve the LM performance on both NLP tasks (e.g., MMLU, TruthfulQA, and HumanEval) and open-ended generation benchmarks (e.g., MT-Bench and AlpacaEval). Remarkably, in the most advantageous case, IM boosts model performance on AlpacaEval 1.0 by over 100%. We identify two key factors influencing the effectiveness of IM: (1) The ratio between instruction length and output length in the training data; and (2) The number of training examples. We observe that IM is especially beneficial when trained on datasets with lengthy instructions paired with brief outputs, or under the Superficial Alignment Hypothesis (SAH) where a small amount of training examples are used for instruction tuning. Further analysis substantiates our hypothesis that the improvement can be attributed to reduced overfitting to instruction tuning datasets. Our work provides practical guidance for instruction tuning LMs, especially in low-resource scenarios.

Large Language Models for code (code LLMs) have witnessed tremendous progress in recent years. With the rapid development of code LLMs, many popular evaluation benchmarks, such as HumanEval, DS-1000, and MBPP, have emerged to measure the performance of code LLMs with a particular focus on code generation tasks. However, they are insufficient to cover the full range of expected capabilities of code LLMs, which span beyond code generation to answering diverse coding-related questions. To fill this gap, we propose InfiBench, the first large-scale freeform question-answering (QA) benchmark for code to our knowledge, comprising 234 carefully selected high-quality Stack Overflow questions that span across 15 programming languages. InfiBench uses four types of model-free automatic metrics to evaluate response correctness where domain experts carefully concretize the criterion for each question. We conduct a systematic evaluation for over 100 latest code LLMs on InfiBench, leading to a series of novel and insightful findings. Our detailed analyses showcase potential directions for further advancement of code LLMs. InfiBench is fully open source and continuously expanding to foster more scientific and systematic practices for code LLM evaluation.

Benchmarks are essential for consistent evaluation and reproducibility. The integration of Artificial Intelligence into Software Engineering (AI4SE) has given rise to numerous benchmarks for tasks such as code generation and bug fixing. However, this surge presents challenges: (1) scattered benchmark knowledge across tasks, (2) difficulty in selecting relevant benchmarks, (3) the absence of a uniform standard for benchmark development, and (4) limitations of existing benchmarks. In this paper, we review 173 studies and identify 204 AI4SE benchmarks. We classify these benchmarks, analyze their limitations, and expose gaps in practices. Based on our review, we created BenchScout, a semantic search tool to find relevant benchmarks, using automated clustering of the contexts from associated studies. We conducted a user study with 22 participants to evaluate BenchScout's usability, effectiveness, and intuitiveness which resulted in average scores of 4.5, 4.0, and 4.1 out of 5. To advance benchmarking standards, we propose BenchFrame, a unified method to enhance benchmark quality. As a case study, we applied BenchFrame to the HumanEval benchmark and addressed its main limitations. This led to HumanEvalNext, featuring (1) corrected errors, (2) improved language conversion, (3) expanded test coverage, and (4) increased difficulty. We then evaluated ten state-of-the-art code language models on HumanEval, HumanEvalPlus, and HumanEvalNext. On HumanEvalNext, models showed a pass@1 score reduction of 31.22% and 19.94% compared to HumanEval and HumanEvalPlus, respectively.

Large language models (LLMs) have made significant progress in generating codes from textual prompts. However, existing benchmarks have mainly concentrated on translating English prompts to multilingual codes or have been constrained to very limited natural languages (NLs). These benchmarks have overlooked the vast landscape of massively multilingual NL to multilingual code, leaving a critical gap in the evaluation of multilingual LLMs. In response, we introduce HumanEval-XL, a massively multilingual code generation benchmark specifically crafted to address this deficiency. HumanEval-XL establishes connections between 23 NLs and 12 programming languages (PLs), and comprises of a collection of 22,080 prompts with an average of 8.33 test cases. By ensuring parallel data across multiple NLs and PLs, HumanEval-XL offers a comprehensive evaluation platform for multilingual LLMs, allowing the assessment of the understanding of different NLs. Our work serves as a pioneering step towards filling the void in evaluating NL generalization in the area of multilingual code generation. We make our evaluation code and data publicly available at https://github.com/FloatAI/HumanEval-XL.

Recent advancements in large language models (LLMs) have significantly enhanced code generation from natural language prompts. The HumanEval Benchmark, developed by OpenAI, remains the most widely used code generation benchmark. However, this and other Code LLM benchmarks face critical limitations, particularly in task diversity, test coverage, and linguistic scope. Current evaluations primarily focus on English-to-Python conversion tasks with limited test cases, potentially overestimating model performance. While recent works have addressed test coverage and programming language (PL) diversity, code generation from low-resource language prompts remains largely unexplored. To address this gap, we introduce mHumanEval, an extended benchmark supporting prompts in over 200 natural languages. We employ established machine translation methods to compile the benchmark, coupled with a quality assurance process. Furthermore, we provide expert human translations for 15 diverse natural languages (NLs). We conclude by analyzing the multilingual code generation capabilities of state-of-the-art (SOTA) Code LLMs, offering insights into the current landscape of cross-lingual code generation.

We introduce Codex, a GPT language model fine-tuned on publicly available code from GitHub, and study its Python code-writing capabilities. A distinct production version of Codex powers GitHub Copilot. On HumanEval, a new evaluation set we release to measure functional correctness for synthesizing programs from docstrings, our model solves 28.8% of the problems, while GPT-3 solves 0% and GPT-J solves 11.4%. Furthermore, we find that repeated sampling from the model is a surprisingly effective strategy for producing working solutions to difficult prompts. Using this method, we solve 70.2% of our problems with 100 samples per problem. Careful investigation of our model reveals its limitations, including difficulty with docstrings describing long chains of operations and with binding operations to variables. Finally, we discuss the potential broader impacts of deploying powerful code generation technologies, covering safety, security, and economics.

We introduce a principled probabilistic framework for reward-guided decoding in large language models, addressing the limitations of standard decoding methods that optimize token-level likelihood rather than sequence-level quality. Our method defines a reward-augmented target distribution over complete sequences by combining model transition probabilities with prefix-dependent reward potentials. Importantly, the approach is training-free: it leaves model weights unchanged and instead modifies the inference distribution via reward potentials, with all gains arising purely from inference-time sampling. To sample from this distribution, we develop Sequential Monte Carlo algorithms, including a computationally efficient prefix-only variant and a lookahead variant whose intermediate targets match the exact marginals of the full sequence distribution. The framework also integrates resample-move updates with Metropolis-Hastings rejuvenation and supports block-wise generation, subsuming common decoding strategies such as temperature sampling and power-tempered objectives. Empirical results across three 7B models show significant gains. On code generation (HumanEval), our method improves base performance by up to 54.9% and surpasses the strongest sampling baselines by 9.1%-15.3%. On mathematical reasoning (MATH500), it achieves gains of up to 8.8%. Notably, it reaches 87.8% on HumanEval and 78.4% on MATH500 with Qwen2.5-7B, consistently outperforming the reinforcement learning method GRPO.

We introduce GDPval, a benchmark evaluating AI model capabilities on real-world economically valuable tasks. GDPval covers the majority of U.S. Bureau of Labor Statistics Work Activities for 44 occupations across the top 9 sectors contributing to U.S. GDP (Gross Domestic Product). Tasks are constructed from the representative work of industry professionals with an average of 14 years of experience. We find that frontier model performance on GDPval is improving roughly linearly over time, and that the current best frontier models are approaching industry experts in deliverable quality. We analyze the potential for frontier models, when paired with human oversight, to perform GDPval tasks cheaper and faster than unaided experts. We also demonstrate that increased reasoning effort, increased task context, and increased scaffolding improves model performance on GDPval. Finally, we open-source a gold subset of 220 tasks and provide a public automated grading service at evals.openai.com to facilitate future research in understanding real-world model capabilities.

With generative AI advances, the exciting potential for autonomous agents to manage daily tasks via natural language commands has emerged. However, cur rent agents are primarily created and tested in simplified synthetic environments, substantially limiting real-world scenario representation. In this paper, we build an environment for agent command and control that is highly realistic and reproducible. Specifically, we focus on agents that perform tasks on websites, and we create an environment with fully functional websites from four common domains: e-commerce, social forum discussions, collaborative software development, and content management. Our environment is enriched with tools (e.g., a map) and external knowledge bases (e.g., user manuals) to encourage human-like task-solving. Building upon our environment, we release a set of benchmark tasks focusing on evaluating the functional correctness of task completions. The tasks in our benchmark are diverse, long-horizon, and are designed to emulate tasks that humans routinely perform on the internet. We design and implement several autonomous agents, integrating recent techniques such as reasoning before acting. The results demonstrate that solving complex tasks is challenging: our best GPT-4-based agent only achieves an end-to-end task success rate of 10.59%. These results highlight the need for further development of robust agents, that current state-of-the-art LMs are far from perfect performance in these real-life tasks, and that WebArena can be used to measure such progress. Our code, data, environment reproduction resources, and video demonstrations are publicly available at https://webarena.dev/.

Code large language models (LLMs) enhance programming by understanding and generating code across languages, offering intelligent feedback, bug detection, and code updates through reflection, improving development efficiency and accessibility. While benchmarks (e.g. HumanEval/LiveCodeBench) evaluate code generation and real-world relevance, previous works ignore the scenario of modifying code in repositories. Considering challenges remaining in improving reflection capabilities and avoiding data contamination in dynamic benchmarks, we introduce LiveRepoReflection, a challenging benchmark for evaluating code understanding and generation in multi-file repository contexts, featuring 1,888 rigorously filtered test cases across 6 programming languages to ensure diversity, correctness, and high difficulty. Further, we create RepoReflection-Instruct, a large-scale, quality-filtered instruction-tuning dataset derived from diverse sources, used to train RepoReflectionCoder through a two-turn dialogue process involving code generation and error-driven repair. The leaderboard evaluates over 40 LLMs to reflect the model performance of repository-based code reflection.

Recent advancements in large language models (LLMs) have greatly improved code generation, specifically at the function level. For instance, GPT-4 has achieved an 88.4% pass rate on HumanEval. However, this draws into question the adequacy of existing benchmarks in thoroughly assessing function-level code generation capabilities. Our study analyzed two common benchmarks, HumanEval and MBPP, and found that these might not thoroughly evaluate LLMs' code generation capacities due to limitations in quality, difficulty, and granularity. To resolve this, we introduce the Mostly Hard Python Problems (MHPP) dataset, consisting of 140 unique human-curated problems. By focusing on the combination of natural language and code reasoning, MHPP gauges LLMs' abilities to comprehend specifications and restrictions, engage in multi-step reasoning, and apply coding knowledge effectively. Initial evaluations of 22 LLMs using MHPP showed many high-performing models on HumanEval failed to achieve similar success on MHPP. Moreover, MHPP highlighted various previously undiscovered limitations within various LLMs, leading us to believe that it could pave the way for a better understanding of LLMs' capabilities and limitations. Dataset and code are available at https://github.com/SparksofAGI/MHPP.

Program synthesis has been long studied with recent approaches focused on directly using the power of Large Language Models (LLMs) to generate code. Programming benchmarks, with curated synthesis problems and test-cases, are used to measure the performance of various LLMs on code synthesis. However, these test-cases can be limited in both quantity and quality for fully assessing the functional correctness of the generated code. Such limitation in the existing benchmarks begs the following question: In the era of LLMs, is the code generated really correct? To answer this, we propose EvalPlus -- a code synthesis evaluation framework to rigorously benchmark the functional correctness of LLM-synthesized code. EvalPlus augments a given evaluation dataset with large amounts of test-cases newly produced by an automatic test input generator, powered by both LLM- and mutation-based strategies. While EvalPlus is general, we extend the test-cases of the popular HumanEval benchmark by 80x to build HumanEval+. Our extensive evaluation across 26 popular LLMs (e.g., GPT-4 and ChatGPT) demonstrates that HumanEval+ is able to catch significant amounts of previously undetected wrong code synthesized by LLMs, reducing the pass@k by up-to 19.3-28.9%. We also surprisingly found that test insufficiency can lead to mis-ranking. For example, both WizardCoder-CodeLlama and Phind-CodeLlama now outperform ChatGPT on HumanEval+, while none of them could on HumanEval. Our work not only indicates that prior popular code synthesis evaluation results do not accurately reflect the true performance of LLMs for code synthesis, but also opens up a new direction to improve such programming benchmarks through automated testing. We have open-sourced our tools, enhanced datasets as well as all LLM-generated code at https://github.com/evalplus/evalplus to facilitate and accelerate future LLM-for-code research.

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.

This paper presents HerO 2, Team HUMANE's system for the AVeriTeC shared task at the FEVER-25 workshop. HerO 2 is an enhanced version of HerO, the best-performing open-source model from the previous year's challenge. It improves evidence quality through document summarization and answer reformulation, optimizes veracity prediction via post-training quantization under computational constraints, and enhances overall system performance by integrating updated language model (LM) backbones. HerO 2 ranked second on the leaderboard while achieving the shortest runtime among the top three systems, demonstrating both high efficiency and strong potential for real-world fact verification. The code is available at https://github.com/ssu-humane/HerO2.

Autonomous agents powered by large language models (LLMs) show promising potential in assistive tasks across various domains, including mobile device control. As these agents interact directly with personal information and device settings, ensuring their safe and reliable behavior is crucial to prevent undesirable outcomes. However, no benchmark exists for standardized evaluation of the safety of mobile device-control agents. In this work, we introduce MobileSafetyBench, a benchmark designed to evaluate the safety of device-control agents within a realistic mobile environment based on Android emulators. We develop a diverse set of tasks involving interactions with various mobile applications, including messaging and banking applications. To clearly evaluate safety apart from general capabilities, we design separate tasks measuring safety and tasks evaluating helpfulness. The safety tasks challenge agents with managing potential risks prevalent in daily life and include tests to evaluate robustness against indirect prompt injections. Our experiments demonstrate that while baseline agents, based on state-of-the-art LLMs, perform well in executing helpful tasks, they show poor performance in safety tasks. To mitigate these safety concerns, we propose a prompting method that encourages agents to prioritize safety considerations. While this method shows promise in promoting safer behaviors, there is still considerable room for improvement to fully earn user trust. This highlights the urgent need for continued research to develop more robust safety mechanisms in mobile environments. We open-source our benchmark at: https://mobilesafetybench.github.io/.

We present RepoST, a scalable method to construct environments that provide execution feedback for repository-level code generation for both training and evaluation. Unlike existing works that aim to build entire repositories for execution, which is challenging for both human and LLMs, we provide execution feedback with sandbox testing, which isolates a given target function and its dependencies to a separate script for testing. Sandbox testing reduces the complexity of external dependencies and enables constructing environments at a large scale. We use our method to construct RepoST-Train, a large-scale train set with 7,415 functions from 832 repositories. Training with the execution feedback provided by RepoST-Train leads to a performance gain of 5.5% Pass@1 on HumanEval and 3.5% Pass@1 on RepoEval. We also build an evaluation dataset, RepoST-Eval, and benchmark 12 code generation models.

Code benchmarks such as HumanEval are widely adopted to evaluate the capabilities of Large Language Models (LLMs), providing insights into their strengths and weaknesses. However, current benchmarks primarily exercise LLMs' capability on common coding tasks (e.g., bubble sort, greatest common divisor), leaving domain-specific coding tasks (e.g., computation, system, cryptography) unexplored. To fill this gap, we propose a multi-domain code benchmark, DOMAINEVAL, designed to evaluate LLMs' coding capabilities thoroughly. Our pipeline works in a fully automated manner, enabling a push-bottom construction from code repositories into formatted subjects under study. Interesting findings are observed by evaluating 12 representative LLMs against DOMAINEVAL. We notice that LLMs are generally good at computation tasks while falling short on cryptography and system coding tasks. The performance gap can be as much as 68.94% (80.94% - 12.0%) in some LLMs. We also observe that generating more samples can increase the overall performance of LLMs, while the domain bias may even increase. The contributions of this study include a code generation benchmark dataset DOMAINEVAL, encompassing six popular domains, a fully automated pipeline for constructing code benchmarks, and an identification of the limitations of LLMs in code generation tasks based on their performance on DOMAINEVAL, providing directions for future research improvements. The leaderboard is available at https://domaineval.github.io/.

Large language models (LLMs) have significantly improved their ability to perform tasks in the field of code generation. However, there is still a gap between LLMs being capable coders and being top-tier software engineers. Based on the observation that top-level software engineers often ask clarifying questions to reduce ambiguity in both requirements and coding solutions, we argue that the same should be applied to LLMs for code generation tasks. In this work, we conducted an empirical study on the benchmark and analysis of the communication skills of LLMs for code generation. We define communication skills of LLMs as ``being able to ask clarifying questions when the description of the code generation problem has issues''. We created a new benchmark, HumanEvalComm, by modifying problem descriptions according to three issues: inconsistency, ambiguity, incompleteness. We defined new evaluation metrics such as Communication Rate and Good Question Rate, and then experimented on HumanEvalComm with different Code LLMs, and a new LLM agent approach, Okanagan, to identify and ask questions in ambiguous parts from code and descriptions for further refining the generated code. Finally, we discussed evaluation results by comparing Code LLMs and Okanagan with our findings.