AI RESEARCH
AlignEvoSkill: Towards Knowledge-Aware and Task-Aligned Agent Skill Evolution
arXiv CS.CL
•
ArXi:2506.23149v2 Announce Type: replace Reusable skills play a key role in improving LLM-based agents, but existing skill-evolution methods often fail to ensure that evolved skills both cover the knowledge required by the task and remain aligned with the target task. As a result, evolved skills could be incomplete or irrelevant. To address this limitation, we propose AlignEvoSkill, a skill-evolution framework that jointly models knowledge coverage and task alignment. Given failed task trajectories, AlignEvoSkill first identifies task-relevant knowledge.