AutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI Collaboration
Paper • 2605.20025 • Published • 182
Continual learning
-
-
OpenComputer: Verifiable Software Worlds for Computer-Use Agents
Paper • 2605.19769 • Published • 57 -
WildClawBench: A Benchmark for Real-World, Long-Horizon Agent Evaluation
Paper • 2605.10912 • Published • 45 -
EvolveMem:Self-Evolving Memory Architecture via AutoResearch for LLM Agents
Paper • 2605.13941 • Published • 24 -
HAGE: Harnessing Agentic Memory via RL-Driven Weighted Graph Evolution
Paper • 2605.09942 • Published • 15 -
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 • 3 -
δ-mem: Efficient Online Memory for Large Language Models
Paper • 2605.12357 • Published • 122 -
Learning, Fast and Slow: Towards LLMs That Adapt Continually
Paper • 2605.12484 • Published • 17 -
Continual Harness: Online Adaptation for Self-Improving Foundation Agents
Paper • 2605.09998 • Published • 17 -
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 • 15