开源多智能体框架让大模型深度搜索更透明、可复现。
ManuSearch: Democratizing Deep Search in Large Language Models with a Transparent and Open Multi-Agent Framework
- 分三步：规划问题、实时搜网、提取网页关键信息。
- 在中英文长尾实体推理任务上超越主流闭源系统。
- 适合研究开放深度搜索的开发者和学术界人士。
近期基于网络增强的大语言模型在复杂推理任务中表现优异，但这些能力大多被封闭在专有系统中，架构不透明。本文提出 extbf{ManuSearch}，一个透明且模块化的多智能体框架，旨在让大模型的深度搜索能力民主化。该框架将搜索与推理过程分解为三个协作智能体：(1) 解决方案规划智能体，迭代生成子查询；(2) 网络搜索智能体，通过实时网络搜索获取相关文档；(3) 结构化网页阅读智能体，从原始网页内容中提取关键证据。为严格评估深度推理能力，我们引入 extbf{ORION}，一个聚焦于长尾实体的开放式网络推理基准，涵盖中英文。实验表明，ManuSearch 显著优于现有开源基线，甚至超越领先闭源系统。本工作为开放深度搜索系统的可复现、可扩展研究铺平道路。数据与代码已开源：https://github.com/RUCAIBox/ManuSearch。
原文摘要 · Abstract (English)
Recent advances in web-augmented large language models (LLMs) have exhibited strong performance in complex reasoning tasks, yet these capabilities are mostly locked in proprietary systems with opaque architectures. In this work, we propose \textbf{ManuSearch}, a transparent and modular multi-agent framework designed to democratize deep search for LLMs. ManuSearch decomposes the search and reasoning process into three collaborative agents: (1) a solution planning agent that iteratively formulates sub-queries, (2) an Internet search agent that retrieves relevant documents via real-time web search, and (3) a structured webpage reading agent that extracts key evidence from raw web content. To rigorously evaluate deep reasoning abilities, we introduce \textbf{ORION}, a challenging benchmark focused on open-web reasoning over long-tail entities, covering both English and Chinese. Experimental results show that ManuSearch substantially outperforms prior open-source baselines and even surpasses leading closed-source systems. Our work paves the way for reproducible, extensible research in open deep search systems. We release the data and code in https://github.com/RUCAIBox/ManuSearch
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。