[2603.03292] From Conflict to Consensus: Boosting Medical Reasoning via Multi-Round Agentic RAG

Computer Science > Computation and Language arXiv:2603.03292 (cs) [Submitted on 6 Feb 2026] Title:From Conflict to Consensus: Boosting Medical Reasoning via Multi-Round Agentic RAG Authors:Wenhao Wu, Zhentao Tang, Yafu Li, Shixiong Kai, Mingxuan Yuan, Zhenhong Sun, Chunlin Chen, Zhi Wang View a PDF of the paper titled From Conflict to Consensus: Boosting Medical Reasoning via Multi-Round Agentic RAG, by Wenhao Wu and 7 other authors View PDF HTML (experimental) Abstract: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(LLMs) exhibit high reasoning capacity in medical question-answering, but their tendency to produce hallucinations and outdated knowledge poses critical risks in healthcare fields.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. In the paper, we propose **MA-RAG** (**M**ulti-Round **A**gentic RAG), a framework that facilitates test-time scaling for complex medical reasoning by iteratively evolving both external evidence and internal reasoning history within an agentic refinement loop. At each round, the agent transforms semantic **conflict** among candidate responses into actionable queries to retrieve external evidence, while optimizing history reasoning traces to mitigate long-context degradation. MA-RAG extends the *self-consistency* principle by leveraging the lack of consistency as a proactive signal for multi-round agentic reasoning and retriev...