Skill-Pro: Learning Reusable Skills from Experience via Non-Parametric PPO for LLM Agents 事件

Skill-Pro: Learning Reusable Skills from Experience via Non-Parametric PPO for LLM Agents arXiv:2602.01869v3 Announce Type: replace Abstract: LLM-driven agents excel at sequential decision-making but often rely on on-the-fly reasoning, re-deriving solutions even in recurring scenarios. This insufficient experience reuse leads to computational redundancy and instability. To bridge this gap, we propose Skill-Pro, a framework enabling agents to autonomously learn reusable procedural skills from in