MASS-RAG: Multi-Agent Synthesis Retrieval-Augmented Generation
- Published
- Source
- arXiv
- Paper number
- 157
- Field
- Agents / RAG / Multi-Agent
- arXiv ID
- 2604.18509
Key points
- Large language models (LLMs) often generate factually unreliable or hallucinated outputs because they rely on static parametric knowledge.
- Traditional retrieval-augmented generation (RAG) struggles with noisy, incomplete, or irrelevant retrieval context, which degrades generation quality.
- Existing multi-agent RAG frameworks often use a single judging agent for filtering, which limits their ability to identify and exploit diverse, complementary evidence distributed across documents.
- We introduce MASS-RAG, a training-free multi-agent synthesis framework with specialized LLM agents for evidence refinement, selective candidate-answer generation, and final-answer synthesis.
- It uses three distinct filter agents, Summarizer, Extractor, and Reasoner, each of which processes retrieved documents from a unique and complementary perspective to refine query-relevant evidence.
- It uses a selective Answer Agent that independently generates candidate answers from each filtered response, and a Synthesis Agent that combines those candidates or the filtered evidence into a unified final answer.
Paper links
External research summaries. These are not HDATF publications or measured product results.