AI RESEARCH
Dynamic Dual-Granularity Skill Bank for Agentic RL
arXiv CS.AI
•
ArXi:2603.28716v1 Announce Type: new Agentic reinforcement learning (RL) can benefit substantially from reusable experience, yet existing skill-based methods mainly extract trajectory-level guidance and often lack principled mechanisms for maintaining an evolving skill memory. We propose D2Skill, a dynamic dual-granularity skill bank for agentic RL that organizes reusable experience into task skills for high-level guidance and step skills for fine-grained decision and error correction.