AutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI Collaboration
Paper • 2605.20025 • Published • 192
Continual learning
-
-
OpenComputer: Verifiable Software Worlds for Computer-Use Agents
Paper • 2605.19769 • Published • 89 -
WildClawBench: A Benchmark for Real-World, Long-Horizon Agent Evaluation
Paper • 2605.10912 • Published • 47 -
EvolveMem:Self-Evolving Memory Architecture via AutoResearch for LLM Agents
Paper • 2605.13941 • Published • 25 -
HAGE: Harnessing Agentic Memory via RL-Driven Weighted Graph Evolution
Paper • 2605.09942 • Published • 17 -
MemReread: Enhancing Agentic Long-Context Reasoning via Memory-Guided Rereading
Paper • 2605.10268 • Published • 5 -
Towards Self-Evolving Agentic Literature Retrieval
Paper • 2605.14306 • Published • 5 -
δ-mem: Efficient Online Memory for Large Language Models
Paper • 2605.12357 • Published • 133 -
Learning, Fast and Slow: Towards LLMs That Adapt Continually
Paper • 2605.12484 • Published • 19 -
Continual Harness: Online Adaptation for Self-Improving Foundation Agents
Paper • 2605.09998 • Published • 20 -
Safety Alignment as Continual Learning: Mitigating the Alignment Tax via Orthogonal Gradient Projection
Paper • 2602.07892 • Published • 2 -
SkillEvolBench: Benchmarking the Evolution from Episodic Experience to Procedural Skills
Paper • 2605.24117 • Published • 22 -
SkillAdaptor: Self-Adapting Skills for LLM Agents from Trajectories
Paper • 2606.01311 • Published • 37 -
Remember When It Matters: Proactive Memory Agent for Long-Horizon Agents
Paper • 2607.08716 • Published • 16 -
Self-Guided Test-Time Training for Long-Context LLMs
Paper • 2607.09415 • Published • 19 -
SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning
Paper • 2607.14777 • Published • 106 -
DeepSearch-World: Self-Distillation for Deep Search Agents in a Verifiable Environment
Paper • 2607.07820 • Published • 94 -
Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills
Paper • 2607.22529 • Published • 47 -
SkillRise: Agentic Reinforcement Learning for Cross-Task Skill Evolution
Paper • 2607.26784 • Published • 30 -
MemHarness: Memory Is Reconstructed, Not Replayed
Paper • 2607.28272 • Published • 17 -
Progressive Agent Skill Generation via Reinforcement Learning
Paper • 2608.01678 • Published • 60 -
Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA
Paper • 2608.09819 • Published • 342 -
Agent Memory Distillation: Empowering Small LLM Agents with Hierarchical Teacher Memory
Paper • 2608.07169 • Published • 50 -
Harness the Memory: A Holistic Evaluation of Memory Substrates in Memory Agents
Paper • 2608.15008 • Published • 15 -
Prime Agent: A Self-Improving RLM Harness
Paper • 2608.23552 • Published • 48 -
JIT-Agent: Scaling Harness Intelligence via Just-in-Time Harness Evolution
Paper • 2608.25593 • Published • 114 -
WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill Evolution
Paper • 2608.27454 • Published • 24 -
PILOT in the Loop: Live Self-Improvement for Long-Horizon Agents
Paper • 2608.26530 • Published • 30 -
Training Agents to Evolve with Their Harness: TaoLive Digital Avatar Agent Technical Report
Paper • 2608.15763 • Published • 47 -
TTPO: Test-Time Policy Optimization
Paper • 2608.27448 • Published • 77