MASS-RAG：多代理合成检索增强生成
MASS-RAG: Multi-Agent Synthesis Retrieval-Augmented Generation
AI总结：
MASS-RAG通过多代理结构处理证据，提升检索增强生成在噪声、不完整或异质证据下的表现，实验显示其在相关证据分散于检索结果时性能更优。
摘要：
大型语言模型（LLMs）广泛用于检索增强生成（RAG）以在推理时整合外部知识。然而，当检索到的上下文嘈杂、不完整或异质时，单一生成过程往往难以有效整合证据。我们提出MASS-RAG，一种多代理合成方法，将证据处理分解为多个角色专门化的代理。MASS-RAG应用不同的代理进行证据摘要、证据提取和检索文档的推理，并通过专门的合成阶段结合其输出以生成最终答案。此设计暴露了多个中间证据视图，使模型在生成答案前能够比较和整合互补信息。在四个基准测试中，MASS-RAG在强RAG基线中一致提升了性能，特别是在相关证据分散于检索结果的情况下。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
