MASS-RAG: Multi-Agent Synthesis Retrieval-Augmented Generation
Xingchen Xiao, Heyan Huang, Runheng Liu, Jincheng Xie
TLDR
MASS-RAG is a multi-agent RAG system that uses specialized agents to process and synthesize diverse evidence, improving performance with noisy contexts.
Key contributions
- Introduces MASS-RAG, a multi-agent synthesis approach for Retrieval-Augmented Generation.
- Utilizes role-specialized agents for evidence summarization, extraction, and reasoning.
- Combines agent outputs through a dedicated synthesis stage for final answer generation.
- Exposes intermediate evidence views, enabling better comparison and integration of information.
Why it matters
This paper addresses a key limitation of RAG systems: effectively handling diverse and noisy retrieved information. By using a multi-agent approach, MASS-RAG significantly improves performance, especially when evidence is scattered. This advancement makes RAG more robust and reliable for real-world applications.
Original Abstract
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.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.