从冲突到共识：通过多轮代理RAG提升医疗推理
From Conflict to Consensus: Boosting Medical Reasoning via Multi-Round Agentic RAG
AI总结：
本文提出MA-RAG框架，通过多轮代理循环迭代优化外部证据和内部推理历史，提升医疗复杂推理能力，实验显示在7个医疗问答基准上表现优于现有方法。
摘要：
大型语言模型（LLMs）在医疗问答中表现出高推理能力，但其产生幻觉和过时知识的倾向对医疗领域构成重大风险。虽然检索增强生成（RAG）缓解了这些问题，但现有方法依赖于噪声的token级信号，并缺乏复杂推理所需的多轮细化。本文提出MA-RAG（多轮代理RAG），通过在代理细化循环中迭代演变外部证据和内部推理历史，实现复杂医疗推理的测试时间扩展。在每一轮中，代理将候选响应间的语义冲突转换为可检索的外部证据查询，同时优化历史推理轨迹以缓解长上下文退化。MA-RAG通过利用不一致性作为主动信号来扩展自我一致性原则，并通过迭代最小化残差误差来实现稳定、高保真的医疗共识。在7个医疗问答基准上的广泛评估显示，MA-RAG在推理时间扩展和RAG基线方面均优于竞争方法，平均准确率比基础模型提高+6.8点。我们的代码可在https://github.com/NJU-RL/MA-RAG上获得。
英文摘要：
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(LLMs) exhibit high reasoning capacity in medical question-answering, but their tendency to produce hallucinations and outdated knowledge poses critical risks in healthcare fields.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 this paper, we propose MA-RAG (Multi-Round Agentic 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 retrieval, and mirrors a boosting mechanism that iteratively minimizes the residual error toward a stable, high-fidelity medical consensus. Extensive evaluations across 7 medical Q&A benchmarks show that MA-RAG consistently surpasses competitive inference-time scaling and RAG baselines, delivering substantial +6.8 points on average accuracy over the backbone model. Our code is available at https://github.com/NJU-RL/MA-RAG.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
