用API代替网页浏览，让AI智能体完成网络任务更高效。
Beyond Browsing: API-Based Web Agents
- 设计纯调用API的智能体和混合使用浏览与API的双模式智能体。
- 在WebArena基准上，混合智能体成功率38.9%，比纯浏览提升24.0%。
- 适合需要高效率执行网络任务的研究者与开发者参考。
网页浏览器是人类进行网络活动的主要入口，因此学术界已有大量研究聚焦于通过网页浏览与互联网交互的AI智能体。然而，还存在另一种专为机器设计的接口——应用编程接口（API）。本文探讨：若将传统由浏览代理完成的任务，改由智能体直接调用API来实现，会如何？为此，我们提出两类智能体：(1) 仅通过API执行任务的调用型智能体，类似传统代码生成代理；(2) 可同时使用网页浏览与API的混合型智能体。在广泛使用的真实世界网页导航基准WebArena上的实验表明，基于API的智能体优于纯浏览代理。混合智能体在各类任务中几乎全面领先，相比仅使用浏览的方式提升超过24.0%的绝对性能，达成38.9%的成功率，成为目前无任务特异性智能体中的最先进水平。结果强烈表明，在有可用API时，其作为替代网页浏览的手段具有显著优势。
原文摘要 · Abstract (English)
Web browsers are a portal to the internet, where much of human activity is undertaken. Thus, there has been significant research work in AI agents that interact with the internet through web browsing. However, there is also another interface designed specifically for machine interaction with online content: application programming interfaces (APIs). In this paper we ask -- what if we were to take tasks traditionally tackled by Browsing Agents, and give AI agents access to APIs? To do so, we propose two varieties of agents: (1) an API-calling agent that attempts to perform online tasks through APIs only, similar to traditional coding agents, and (2) a Hybrid Agent that can interact with online data through both web browsing and APIs. In experiments on WebArena, a widely-used and realistic benchmark for web navigation tasks, we find that API-Based Agents outperform web Browsing Agents. Hybrid Agents out-perform both others nearly uniformly across tasks, resulting in a more than 24.0% absolute improvement over web browsing alone, achieving a success rate of 38.9%, the SOTA performance among task-agnostic agents. These results strongly suggest that when APIs are available, they present an attractive alternative to relying on web browsing alone.
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。