SkillWeaver：网络智能体可通过发现与精进技能实现自我提升

摘要

为了在复杂环境中生存并蓬勃发展，人类通过环境探索、将经验分层抽象为可重用技能，以及协作构建不断增长的技能库，进化出了精妙的自我提升机制。尽管近期取得了进展，自主网络代理仍缺乏关键的自我提升能力，在程序性知识抽象、技能精炼及技能组合方面面临挑战。本研究提出了SkillWeaver，一个以技能为核心的框架，使代理能够通过自主合成可重用的API技能实现自我提升。面对新网站，代理自主发现技能，执行以实践，并将实践经验提炼为稳健的API。通过迭代探索，持续扩展轻量级、即插即用的API库，显著增强代理的能力。在WebArena及真实网站上的实验验证了SkillWeaver的有效性，分别实现了31.8%和39.8%的相对成功率提升。此外，由强代理合成的API通过可转移技能显著增强了弱代理，在WebArena上带来了高达54.3%的改进。这些结果证明了将多样化的网站交互精炼为API的有效性，这些API能够在不同网络代理间无缝共享。

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.

SkillWeaver：网络智能体可通过发现与精进技能实现自我提升

SkillWeaver: Web Agents can Self-Improve by Discovering and Honing Skills

摘要

Summary

Support

Support