SkillPlumber:基于指令级覆盖的智能体技能自进化框架
Evolve Where It Matters: Coverage-Guided Self-Evolution of Agent Skills
做智能体技能库的人该看看这篇。它把每次运行拆到指令级别,分清是指令写错还是没被执行,只改真正有问题的地方。比按结果整体打分的主流自进化方法高 8.7 到 14 个百分点,思路可以直接借到自己的 agent 工作流里。
论文提出 SkillPlumber,一个让智能体自我进化技能(skills)的框架。核心是利用指令级覆盖(instruction-level coverage)把每条运行记录中的指令标注为 follow、not-follow 或 not covered,从而区分失败是源于指令写错了还是智能体没有照做。一个持久的根因分析智能体把每个标签转化为修订问题,并在下一次运行中检验修订效果;一个维护者智能体则把跨任务的调查结果蒸馏成共享策略库。在三套基准和三个执行器上,SkillPlumber 解决 64.7% 到 70.5% 的任务,比初始技能高 25.6 到 30.4 个百分点,比最强基线高 8.7 到 14.0 个百分点;在 SkillsBench 上用 GPT-5.5 时,去掉覆盖信号会使恢复的失败减少 20.8%。
现有自进化方法按整体结果评判每次运行,无法定位失败原因,SkillPlumber 的贡献在于把失败归因细化到指令级别,只在实际暴露短板的地方修改技能。对开发者而言,这意味着技能库可以更精准地迭代,避免把执行偏差误判为指令缺陷而引入坏修订。
Evolve Where It Matters: Coverage-Guided Self-Evolution of Agent Skills
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.
本条情报归属 AITOP「论文」核心栏目,重点聚焦北美前沿实验室与硅谷科技巨头。在跨区域产业观察坐标中,该动态直接关联「AI 开发者工具链、Coding Agent 与工程化实践」研究主线,反映出当前技术演进与商业落地的最新风向。涉及核心实体与技术议题包括:SkillPlumber、智能体、SkillsBench、GPT-5.5,读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。
信源核验说明:本文原始线索采编自「arXiv cs.AI」(@Boyin Tan, Jiadong Zhang, Xiaosong Ma, Chun Jason Xue, Xiaowei Huang, Youcheng Sun),经 AITOP 多维评分管线结构化提炼。