cs.CLNov 19, 2026

Evolve Where It Matters: Coverage-Guided Self-Evolution of Agent Skills

Authors: Boyin Tan, Jiadong Zhang, Xiaosong Ma, Chun Jason Xue, Xiaowei Huang, Youcheng Sun

Organizations: Mohamed bin Zayed University of Artificial Intelligence · University of Liverpool

Abstract

Agent skills package procedural knowledge as natural-language instructions, and a skill helps only when its instructions are correct and properly followed by the agent. Self-evolving agents revise their own skills from the runs they make, but existing methods judge each run as a whole, by its outcome or by where it went wrong, and cannot tell whether a failure comes from a wrong instruction or from one the agent did not follow. Instruction-level coverage was introduced to test skills and labels each instruction of a run as follow, not-follow, or not covered, which separates these causes. We leverage it for skill self-evolution with SkillPlumber, a framework in which an agent evolves its own skills where coverage shows they fall short. A persistent root cause analysis agent turns each label into a revision question and checks each revision against the next run, while a maintainer distills investigations across tasks into a shared strategy library. Across three benchmarks and three executors, SkillPlumber solves 64.7% to 70.5% of the tasks, 25.6 to 30.4 percentage points higher than the initial skill and 8.7 to 14.0 percentage points higher than the strongest baseline, and removing coverage reduces recovered failures by 20.8% on SkillsBench with GPT-5.5.

Figures & tables

Appendix figures & tables9 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. EvoSkill: Automated Skill Discovery for Multi-Agent Systems

    Mar 3, 2026Salaheddin Alzubi, Noah Provenzano, Jaydon Bingham +2Agent Skill LearningLLM Agent Self-Improvement

  2. How Feedback-Free Self-Evolution Reshapes Agent Skills: A Systematic Study

    Nov 19, 2026Litao Guo, Man Chen, Xinli Xu +3LLM Agent Skill LearningSelf-Evolving Agents

  3. SkillSmith: Co-Evolving Skills and Tools for Self-Improving Agent Systems

    May 31, 2026Yangbo Wei, Zhen Huang, Shaoqiang Lu +4Tool-Using AgentsAgent Skill Learning