MASS-RAG: Multi-Agent Synthesis Retrieval-Augmented Generation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918458785005568 |
|---|---|
| author | Xiao, Xingchen Huang, Heyan Liu, Runheng Xie, Jincheng |
| author_facet | Xiao, Xingchen Huang, Heyan Liu, Runheng Xie, Jincheng |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_18509 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | MASS-RAG: Multi-Agent Synthesis Retrieval-Augmented Generation Xiao, Xingchen Huang, Heyan Liu, Runheng Xie, Jincheng Computation and Language 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. |
| title | MASS-RAG: Multi-Agent Synthesis Retrieval-Augmented Generation |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2604.18509 |