让网页智能体学会使用网站内置功能，自动完成复杂操作。
WALT: Web Agents that Learn Tools
- 将网站隐藏功能抽象为可调用工具，如搜索、筛选、发布等。
- 在视觉网页任务中成功率更高，步骤更少，依赖大模型推理更少。
- 适合需要稳定浏览器自动化且避免繁琐点击的开发者和研究者。
网页智能体有望自动化复杂浏览器任务，但现有方法脆弱——依赖逐步界面交互和大量大模型推理，在动态布局和长序列任务中容易失效。人类则善于利用网站提供的高阶功能，如搜索、筛选、排序。我们提出WALT（Web Agents that Learn Tools），一种将网站潜在功能逆向工程为可复用工具的框架。WALT不依赖临时假设技能，而是暴露网站已设计好的自动化能力，涵盖发现（搜索、筛选、排序）、通信（发帖、评论、点赞）和内容管理（创建、编辑、删除）。工具抽象底层执行细节：智能体无需思考如何点击或输入，只需调用search(query)或create(listing)。这将计算负担从易碎的逐步推理转移到可靠的工具调用。在VisualWebArena和WebArena上，WALT以更少步骤、更低大模型依赖实现更高成功率，建立了一种稳健且可泛化的浏览器自动化范式。
原文摘要 · Abstract (English)
Web agents promise to automate complex browser tasks, but current methods remain brittle -- relying on step-by-step UI interactions and heavy LLM reasoning that break under dynamic layouts and long horizons. Humans, by contrast, exploit website-provided functionality through high-level operations like search, filter, and sort. We introduce WALT (Web Agents that Learn Tools), a framework that reverse-engineers latent website functionality into reusable invocable tools. Rather than hypothesizing ad-hoc skills, WALT exposes robust implementations of automations already designed into websites -- spanning discovery (search, filter, sort), communication (post, comment, upvote), and content management (create, edit, delete). Tools abstract away low-level execution: instead of reasoning about how to click and type, agents simply call search(query) or create(listing). This shifts the computational burden from fragile step-by-step reasoning to reliable tool invocation. On VisualWebArena and WebArena, WALT achieves higher success with fewer steps and less LLM-dependent reasoning, establishing a robust and generalizable paradigm for browser automation.
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。