发表机构
Institute of Software Chinese Academy of Sciences; University of Chinese Academy of Sciences; Beijing University of Post and Telecommunications（中国科学院软件研究所; 中国科学院大学; 北京邮电大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出VCE-Skill，将公共技能变更提炼为结构化版本变更经验并与轨迹提议自适应融合，提升了技能自进化的平均分数，增强了跨模型迁移性能，拓展了技能自进化的先验知识来源。
AI 中文摘要
智能体越来越依赖可复用技能来编码任务知识、工具使用流程和验证规则。现有技能自进化方法主要利用当前任务收集的执行轨迹来修改技能，却未充分利用公共技能版本历史中积累的进化知识。初步研究表明，公共技能变更与执行轨迹存在互补性：公共技能变更提供可复用的进化先验，轨迹则提供当前任务的实证。受此启发，本文提出VCE-Skill，它将嘈杂且具有特定实现性的公共技能变更提炼为可复用、结构化的版本变更经验，并与基础进化器生成的轨迹衍生提议自适应融合，从而在利用外部经验的同时保留任务特定实证。大量实验表明，VCE-Skill可提升技能自进化效果，使平均分数提高3.20至4.98分；迁移实验进一步显示，由此生成的技能实现了更强的跨模型迁移性能。本研究强调公共技能版本变更作为此前未被充分探索但有效的先验知识来源，推动了轨迹驱动的技能自进化发展。
英文摘要
Agents increasingly rely on reusable skills to encode task knowledge, tool-use procedures, and validation rules. Existing skill self-evolution methods primarily revise skills using execution trajectories collected from current tasks, leaving the evolution knowledge accumulated in public skill version histories largely untapped. Our pilot study reveals a clear complementarity between the two sources: public skill changes provide reusable evolution priors, whereas trajectories provide evidence grounded in the current task. Motivated by this, we propose VCE-Skill, which distills noisy and implementation-specific public skill changes into reusable, structured version-change experience and adaptively fuses it with trajectory-derived proposals from the base evolver, thereby exploiting external experience while retaining task-specific evidence. Extensive experiments demonstrate that VCE-Skill improves skill self-evolution, increasing mean scores by 3.20--4.98 points; transfer experiments further show that the resulting skills achieve stronger cross-model transfer performance. Our work highlights public skill version changes as a previously underexplored yet effective source of prior knowledge and advances trajectory-driven skill self-evolution.
