WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill Evolution· WikiSkill：将代理经验编译为持续知识
Agent skills package specialized knowledge and workflows into reusable resources that extend AI agent capabilities. Recent work automatically discovers such skills from agent experience, which enables agents to progressively adapt through interaction. However, the insights that guide skill development typically remain scattered across optimization histories, limiting their systematic reuse across iterations. We introduce WikiSkill, a framework that co-evolves agent skills with a persistent knowledge base (wiki). At a high level, WikiSkill separates raw execution experience, accumulated knowledge, and executable skills, while continuously consolidating experience into the wiki, which subsequent skill updates can build on. Across diverse benchmarks and models, WikiSkill consistently outperfo
将代理经验整合为持久知识，促进技能进化。
- 核心方法
- 引入WikiSkill框架，将执行经验、积累的知识和可执行技能分开处理，并持续将经验整合进知识库。
- 适合谁读
- 适合AI研究者和工程师阅读，特别是关注代理技能进化和知识管理的读者。
- 要解决的问题
- 现有的代理技能开发中，有价值的见解分散在优化历史中，难以系统性重用。
- 关键实验
- 在多个基准和模型上进行了实验，但未提供具体数据。
- 主要贡献
- 实现了代理技能与持久知识库的共同进化，提高技能的系统性和可重用性。
- 意义与局限
- 该框架有助于AI代理通过互动逐步适应和改进技能，但可能受限于知识库的初始质量和更新频率。