让多智能体系统自动找对专家，复杂问题分步解决。
Talk to Right Specialists: Iterative Routing in Multi-agent Systems for Question Answering
- 用嵌入空间总结各智能体知识，精准路由问题
- 单跳问题准确率高，多跳问题通过迭代求解
- 无需训练，适合知识分散的生产环境
由于知识主权限制，本地知识库无法集中，检索增强生成（RAG）智能体被广泛用于问答。但实际部署中常出现两个问题：用户不知该找哪个智能体，复杂问题所需证据分散在多个智能体中。为此，我们提出RIRS，一种无需训练的编排框架，使多智能体系统能高效回答问题。RIRS将每个智能体的本地语料在嵌入空间中摘要，使面向用户的服务器仅将查询路由至最相关的智能体，降低延迟并避免“广播到所有”的噪声上下文。对于复杂问题，服务器可迭代聚合响应，生成中间结果并精炼问题，逐步逼近完整答案。大量实验表明，RIRS能精准选择智能体，对单跳问题给出准确回答；通过迭代策略，对多步复杂问题也能实现高精度求解。
原文摘要 · Abstract (English)
Retrieval-augmented generation (RAG) agents are increasingly deployed to answer questions over local knowledge bases that cannot be centralized due to knowledge-sovereignty constraints. This results in two recurring failures in production: users do not know which agent to consult, and complex questions require evidence distributed across multiple agents. To overcome these challenges, we propose RIRS, a training-free orchestration framework to enable a multi-agent system for question answering. In detail, RIRS summarizes each agent's local corpus in an embedding space, enabling a user-facing server to route queries only to the most relevant agents, reducing latency and avoiding noisy "broadcast-to-all" contexts. For complicated questions, the server can iteratively aggregate responses to derive intermediate results and refine the question to bridge the gap toward a comprehensive answer. Extensive experiments demonstrate the effectiveness of RIRS, including its ability to precisely select agents and provide accurate responses to single-hop queries, and its use of an iterative strategy to achieve accurate, multi-step resolutions for complex queries.
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。