提出新型网页信息聚合框架，提升复杂查询下的多源信息获取能力。
Infogent: An Agent-Based Framework for Web Information Aggregation
- 分直接接口与视觉交互两种方式，构建模块化信息聚合框架
- 在FRAMES数据集上比现有SOTA方法高7%，在AssistantBench上高4.3%
- 适合需要跨网站整合信息的智能搜索、助手类应用
尽管现有网页代理在任务完成基准上表现良好，但大多基于线性动作序列与明确结束状态的预设。本文关注信息聚合型网页导航，要求代理探索多个网站以满足复杂查询。从两种视角出发：(i) 直接API驱动访问，仅依赖文本界面，利用Google Search API导航并用爬虫提取内容；(ii) 交互式视觉访问，使用页面截图并需与浏览器交互。为此，我们提出Infogent框架，包含导航器、提取器和聚合器三个组件。在不同访问模式下实验表明，在FRAMES数据集上，直接接口模式下较现有SOTA多代理搜索框架提升7%；在AssistantBench上，交互视觉模式下较现有信息检索网页代理提升4.3%。
原文摘要 · Abstract (English)
Despite seemingly performant web agents on the task-completion benchmarks, most existing methods evaluate the agents based on a presupposition: the web navigation task consists of linear sequence of actions with an end state that marks task completion. In contrast, our work focuses on web navigation for information aggregation, wherein the agent must explore different websites to gather information for a complex query. We consider web information aggregation from two different perspectives: (i) Direct API-driven Access relies on a text-only view of the Web, leveraging external tools such as Google Search API to navigate the web and a scraper to extract website contents. (ii) Interactive Visual Access uses screenshots of the webpages and requires interaction with the browser to navigate and access information. Motivated by these diverse information access settings, we introduce Infogent, a novel modular framework for web information aggregation involving three distinct components: Navigator, Extractor and Aggregator. Experiments on different information access settings demonstrate Infogent beats an existing SOTA multi-agent search framework by 7% under Direct API-Driven Access on FRAMES, and improves over an existing information-seeking web agent by 4.3% under Interactive Visual Access on AssistantBench.
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。