Agents
CoEvolve: Training LLM Agents via Agent-Data Mutual Evolution
arXiv:2604.15840v1 Announce Type: new Abstract: Reinforcement learning for LLM agents is typically conducted on a static data distribution, which fails to adapt to the agent's evolving behavior and le
arXiv:2604.15840v1 Announce Type: new Abstract: Reinforcement learning for LLM agents is typically conducted on a static data distribution, which fails to adapt to the agent's evolving behavior and leads to poor coverage of complex environment interactions. To address these challenges, we propose CoEvolve, an agent-data mutual evolution framework that enables LLM agents to improve through closed-loop, interaction-driven training. Specifically, CoEvolve extracts feedback signals such as forgetting and uncertainty from rollout trajectories to identify failure-prone interaction patterns, and utilizes them to guide LLM-based task synthesis. The synthesized tasks are validated through environment interaction and utilized to update the data distribution, enabling joint adaptation of the agent and its data. Extensive experiments on AppWorld and BFCL across Qwen2.5-7B, Qwen3-4B, and Qwen3-30B-A3B demonstrate consistent and significant improvements over strong base models, yielding absolute gains of 19.43%, 15.58%, and 18.14%, respectively.
Related
- pi-Play: Multi-Agent Self-Play via Privileged Self-Distillation without External Data
- Remember Me, Refine Me: A Dynamic Procedural Memory Framework for Experience-Driven Agent Evolution
- SkillClaw: Let Skills Evolve Collectively with Agentic Evolver
- Agentic Conversational Search with Contextualized Reasoning via Reinforcement Learning
- Memp: Exploring Agent Procedural Memory
Source: arXiv cs.CL | 2026-04-20