评测大模型网页导航能力，提升复杂信息获取效果
WebWalker: Benchmarking LLMs in Web Traversal
- 设计多智能体框架模拟人类浏览网页，分步探索与评估
- 在真实场景中实现垂直与水平信息整合，显著提升数据质量
- 适合研究RAG与网页交互的学者及产品开发者
检索增强生成（RAG）在开放域问答任务中表现优异，但传统搜索引擎常返回浅层内容，限制大模型处理复杂、多层级信息的能力。为此，我们提出WebWalkerQA基准，用于评估大模型进行网页遍历的能力。该基准衡量模型系统性地访问网站子页面并提取高质量数据的性能。我们进一步提出WebWalker——一种基于‘探索-评判’范式的多智能体框架，模拟人类式网页导航。大量实验表明，WebWalkerQA具有挑战性，且结合WebWalker的RAG在真实场景中实现了横向与纵向的信息融合，有效提升了信息获取能力。
原文摘要 · Abstract (English)
Retrieval-augmented generation (RAG) demonstrates remarkable performance across tasks in open-domain question-answering. However, traditional search engines may retrieve shallow content, limiting the ability of LLMs to handle complex, multi-layered information. To address it, we introduce WebWalkerQA, a benchmark designed to assess the ability of LLMs to perform web traversal. It evaluates the capacity of LLMs to traverse a website's subpages to extract high-quality data systematically. We propose WebWalker, which is a multi-agent framework that mimics human-like web navigation through an explore-critic paradigm. Extensive experimental results show that WebWalkerQA is challenging and demonstrates the effectiveness of RAG combined with WebWalker, through the horizontal and vertical integration in real-world scenarios.
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。