Skip to content

Source paper

SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning

Peng Xia, Jianwen Chen, Hanyang Wang and 10 more

Peng Xia, Jianwen Chen, Hanyang Wang, Jiaqi Liu, Kaide Zeng, Yu Wang, Siwei Han, Yiyang Zhou, Xujiang Zhao, Haifeng Chen, Zeyu Zheng, Cihang Xie, Huaxiu Yao

arXiv 2602.08234 · 202664 upvotes on Hugging Face

Research ideas from this paper (3)

Generated by AI. The paper’s authors did not write these.

AI summary

The paper introduces SKILLRL, a framework that enables LLM agents to learn from past experiences by distilling successful and failed trajectories into a hierarchical skill library (General and Task-Specific) using a teacher model. This library is then used to augment the agent's context during Reinforcement Learning (specifically GRPO), where the skill library recursively evolves based on validation failure modes to continuously improve performance.

How it works (AI summary)

The method utilizes Experience-based Skill Distillation to convert raw trajectories into text-based skills using a powerful teacher model (OpenAI o3). It employs a cold-start Supervised Fine-Tuning (SFT) phase to teach the agent to use these skills, followed by an online RL phase using Group Relative Policy Optimization (GRPO) where the skill library is dynamically updated via recursive evolution.