多智能体协作提升检索增强生成的推理能力
MASS-RAG: Multi-Agent Synthesis Retrieval-Augmented Generation
- 设计多个专业角色智能体分别处理证据摘要、提取与推理
- 在四个基准上优于主流RAG基线，尤其擅长分散证据整合
- 适合需要复杂证据融合的问答场景
大型语言模型广泛应用于推理时引入外部知识的检索增强生成（RAG）。当检索到的上下文存在噪声、不完整或异构时，单一生成过程难以有效整合证据。本文提出多智能体合成检索增强生成（MASS-RAG），将证据处理划分为多个角色专精的智能体：分别负责证据摘要、证据提取和文档推理，并通过专门的合成阶段融合输出以生成最终答案。该设计暴露多个中间证据视图，使模型可在生成前对比和整合互补信息。在四个基准上的实验表明，MASS-RAG持续优于强基线，尤其在相关证据分散于多个检索结果的场景中表现更优。
原文摘要 · Abstract (English)
Large language models (LLMs) are widely used in retrieval-augmented generation (RAG) to incorporate external knowledge at inference time. However, when retrieved contexts are noisy, incomplete, or heterogeneous, a single generation process often struggles to reconcile evidence effectively. We propose \textbf{MASS-RAG}, a multi-agent synthesis approach to retrieval-augmented generation that structures evidence processing into multiple role-specialized agents. MASS-RAG applies distinct agents for evidence summarization, evidence extraction, and reasoning over retrieved documents, and combines their outputs through a dedicated synthesis stage to produce the final answer. This design exposes multiple intermediate evidence views, allowing the model to compare and integrate complementary information before answer generation. Experiments on four benchmarks show that MASS-RAG consistently improves performance over strong RAG baselines, particularly in settings where relevant evidence is distributed across retrieved contexts.
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。