KV-cache sharing boosts multi-agent QA performance but enables undetectable tampering; HMAC manifests binding agent, session, and payload reliably detect changes.
MASS-RAG: Multi-Agent Synthesis Retrieval-Augmented Generation
1 Pith paper cite this work. Polarity classification is still indexing.
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.
fields
cs.MA 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
When Latent Agents Lie: KV-Cache Integrity in Multi-Agent LLM Collaboration
KV-cache sharing boosts multi-agent QA performance but enables undetectable tampering; HMAC manifests binding agent, session, and payload reliably detect changes.