cs.CLNov 10, 2026

Program-Aided Patchable Skill Evolution

Authors: Jiahao Wang, Yuqi Xiong, Qing Yang, Zhipeng Xu, Zhenghao Liu, Zulong Chen, Yubin Bao

Organizations: School of Computer Science and Engineering, Northeastern University, Shenyang, China · Alibaba Group, Hangzhou, China

Abstract

Agent skills have emerged as an effective means of enabling LLM agents to solve complex, interactive tasks by encoding reusable knowledge without modifying model parameters. Recent approaches further improve skill adaptation by distilling reusable experience from agent execution trajectories and evolving skills based on downstream task feedback. However, existing methods primarily represent skills as natural language documents, intertwining procedural logic with descriptive knowledge and making skills difficult to maintain and evolve. To address this limitation, we propose PASE (Program-Aided Patchable Skill Evolution), a program-aided framework that iteratively evolves skills by associating them with executable programs. Unlike prior approaches that encode trajectory-derived experience primarily in natural language, PASE separates reusable procedural logic into editable programs, enabling targeted updates to executable components while reducing the need to repeatedly revise natural language skills. Extensive experiments across diverse models and benchmarks demonstrate that PASE consistently outperforms all baselines, by achieving over 2.8% improvements. Further analyses show that PASE exhibits greater evolutionary stability and generalisation capability, highlighting the critical role of programmatic knowledge in skill evolution. We will release all data and code via GitHub.

Figures & tables

Appendix figures & tables5 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. SkillGrad: Optimizing Agent Skills Like Gradient Descent

    May 26, 2026Hanyu Wang, Yifan Lan, Bochuan Cao +2Large Language Model-Guided OptimizationLLM Agent Self-Improvement

  2. SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision

    May 31, 2026Yuxuan Liu, Zhaochen Su, Lingyun Xie +11LLM Agent Self-ImprovementLLM Agent Skill Learning

  3. SkillAudit: Ground-Truth-Free Skill Evolution via Paired Trajectory Auditing

    Jun 12, 2026Haowen Gao, Haoran Chen, Can Wang +5Algorithmic AuditingLLM Agent Self-Improvement