AI RESEARCH

From Conflict to Consensus: Boosting Medical Reasoning via Multi-Round Agentic RAG

arXiv CS.AI

ArXi:2603.03292v2 Announce Type: replace-cross Large Language Models (LLMs) exhibit high reasoning capacity in medical question-answering, but their tendency to produce hallucinations and outdated knowledge poses critical risks in healthcare fields. While Retrieval-Augmented Generation (RAG) mitigates these issues, existing methods rely on noisy token-level signals and lack the multi-round refinement required for complex reasoning.