让网页智能体自动发现并打磨技能，提升自我能力
SkillWeaver: Web Agents can Self-Improve by Discovering and Honing Skills
- 通过自主发现技能并实践，提炼为可复用API
- 在WebArena上成功率提升31.8%，真实网站达39.8%
- 强代理技能可迁移提升弱代理，最高增益54.3%
为在复杂环境中生存与发展，人类通过环境探索、经验层次抽象形成可复用技能，并协同构建不断增长的技能库。尽管已有进展，自主网页智能体仍缺乏关键自提升能力，难以抽象过程知识、精炼技能或组合技能。本文提出SkillWeaver，一种以技能为中心的框架，使智能体能自主合成可复用的技能API。面对新网站，智能体自主发现技能，执行练习，并将实践经验提炼为健壮的API。迭代探索持续扩展轻量级、即插即用的API库，显著增强智能体能力。在WebArena和真实网站上的实验表明，该方法分别实现31.8%和39.8%的成功率相对提升。此外，强代理合成的API能有效提升弱代理性能，最大提升达54.3%。结果证明，将多样化网站交互提炼为API，可在不同网页智能体间无缝共享。
原文摘要 · Abstract (English)
To survive and thrive in complex environments, humans have evolved sophisticated self-improvement mechanisms through environment exploration, hierarchical abstraction of experiences into reuseable skills, and collaborative construction of an ever-growing skill repertoire. Despite recent advancements, autonomous web agents still lack crucial self-improvement capabilities, struggling with procedural knowledge abstraction, refining skills, and skill composition. In this work, we introduce SkillWeaver, a skill-centric framework enabling agents to self-improve by autonomously synthesizing reusable skills as APIs. Given a new website, the agent autonomously discovers skills, executes them for practice, and distills practice experiences into robust APIs. Iterative exploration continually expands a library of lightweight, plug-and-play APIs, significantly enhancing the agent's capabilities. Experiments on WebArena and real-world websites demonstrate the efficacy of SkillWeaver, achieving relative success rate improvements of 31.8% and 39.8%, respectively. Additionally, APIs synthesized by strong agents substantially enhance weaker agents through transferable skills, yielding improvements of up to 54.3% on WebArena. These results demonstrate the effectiveness of honing diverse website interactions into APIs, which can be seamlessly shared among various web agents.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。