发表机构
Nanjing University; The Hong Kong Polytechnic University（南京大学; 香港理工大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对智能体技能演化中修订与行为证据关联的挑战，提出SkillMorph方法，通过轨迹引导式故障定位优化技能，在基准测试中表现更优且成功应用于自动化内核生成。
AI 中文摘要
智能体技能为代码智能体提供可复用的指导，但不完整或不合适的指导会损害任务执行。为减少技能优化的人工成本，近期方法利用大型语言模型（LLM）从执行反馈中生成修订版本，但将这些修订版本与明确的行为证据关联仍具挑战性。为解决这一差距，我们提出SkillMorph，一种基于智能体技能中轨迹引导式故障定位的技能演化方法，其核心思路是在生成修订版本前将执行证据与特定技能内容关联。具体而言，SkillMorph会对比重复运行及任务中抽象轨迹内的失败与成功证据，并结合演化循环间的变化以识别可疑动作，随后利用这些可疑动作定位技能中的编辑位点并生成对应修订版本。在SWE-Skills-Bench和CannBot上开展的实验显示，SkillMorph演化得到的技能相较于原始技能及四种现有技能演化方法的结果，始终能达到更高的试次级准确率与执行一致性。我们还将SkillMorph应用于AI算子开发团队的自动化内核生成工作，该团队已接受6项技能修订的拉取请求。
英文摘要
Agent skills provide reusable guidance for code agents, but incomplete or unsuitable guidance can impair task execution. To reduce the manual effort of skill refinement, recent approaches use LLMs to generate revisions from execution feedback. However, grounding these revisions in explicit behavioral evidence remains challenging. To address this gap, we propose SkillMorph, a skill-evolution approach based on trajectory-guided fault localization in agent skills. Its core idea is to link execution evidence to specific skill contents before generating revisions. Specifically, SkillMorph compares failure and success evidence in abstracted trajectories across repeated runs and tasks, incorporating changes between evolution loops to identify suspicious actions. It then uses these suspicious actions to localize edit sites in the skills and generate corresponding revisions. Experiments on SWE-Skills-Bench and CannBot show that the skills evolved by SkillMorph consistently achieve higher trial-level accuracy and execution consistency than the original skills and those from four existing skill-evolution methods. We have also applied SkillMorph to automated kernel generation with an AI operator-development team, which has accepted 6 skill-revision pull requests.
Comments20 pages, 3 figures
