通过技能蒸馏实现浏览器上的可扩展行为克隆
Scalable Behaviour Cloning on Browser Using via Skill Distillation
AI总结：
提出通过技能蒸馏将用户交互轨迹转化为自然语言技能，并组织成技能图，实现浏览器代理的可扩展行为克隆。
摘要：
互联网用户通过浏览器集体执行从软件开发、文档编辑到搜索、表单和企业工作流程的大量熟练工作，使得人类浏览成为一种高度可扩展但未充分利用的可重用浏览器技能来源。我们认为，浏览器代理的瓶颈在于不完整信息下的决策而非低级操作，代理缺乏的先验知识已经隐含在人类交互轨迹中。因此，我们通过技能蒸馏研究浏览器代理的可扩展行为克隆，将用户交互轨迹转化为紧凑的自然语言技能，代理可以直接读取、检索、重用和组合这些技能。我们进一步将蒸馏出的技能组织成技能图，使得增长通过巩固而非无界积累进行。这表明，浏览器代理的可扩展性可能更多来自互联网用户已经表达的集体技能，而非手动设计的任务。我们的项目可在以下网址获取：this https URL。
英文摘要：
Internet users collectively perform an enormous range of skilled work through web browsers, from software development and document editing to search, forms, and enterprise workflows, making human browsing a highly scalable but under-exploited source of reusable browser skills. We argue that the bottleneck for browser agents is decision-making under incomplete information rather than low-level operation, and that the priors agents lack are already implicit in human interaction traces. We therefore study scalable behavior cloning for browser agents via skill distillation, converting user interaction trajectories into compact natural-language skills that agents can read, retrieve, reuse, and compose directly. We further organize the distilled skills into a skill graph so that growth proceeds through consolidation rather than unbounded accumulation. This suggests that the scalability of browser agents may come less from manually designed tasks and more from the collective skills already expressed by internet users. Our project is available at: https://lab.einsia.ai/browserbc/.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
