让医疗问答更像医生思考：多智能体协作动态检索。
SEMA-RAG: A Self-Evolving Multi-Agent Retrieval-Augmented Generation Framework for Medical Reasoning
- 拆分医疗推理为解读、探索、裁决三类任务，由不同智能体分工。
- 在五个基准上平均比最强基线高6.46%准确率，跨五种大模型均有效。
- 适合需要可靠证据链的临床决策支持系统研究者使用。
检索增强生成（RAG）广泛用于缓解医疗问答中的幻觉和知识过时风险，但其单轮静态检索机制与临床推理的多阶段特性不匹配。该流程存在两大结构性缺陷：问题到查询的转换常缺乏临床语义理解，且检索缺乏迭代充分性反馈，难以形成可靠证据链。我们认为根本原因在于将解释、探索、裁决等异质任务过度集中在单一推理链中。解决方法是通过任务解耦和动态多轮探索重构流程。为此，我们提出SEMA-RAG，一种自进化多智能体RAG框架，分配三个专业智能体：解读代理负责临床模式解析，探索代理执行基于充分性的自演化检索，裁决代理负责证据评判与答案选择。在五个基准和五种LLM骨干模型上，SEMA-RAG平均比最强基线提升6.46%准确率，按每骨干模型衡量。
原文摘要 · Abstract (English)
Retrieval-Augmented Generation (RAG) is widely employed to mitigate risks such as hallucinations and knowledge obsolescence in medical question answering, yet its predominantly single-round, static retrieval paradigm misaligns with the multi-stage process of clinical reasoning. This compressed workflow induces two structural deficiencies: question-to-query translation often lacks clinically grounded semantic interpretation, and retrieval lacks iterative sufficiency feedback, making it difficult to form reliable evidence chains. We argue that both issues stem from a deeper cause: overloading a single reasoning chain with heterogeneous tasks of interpretation, exploration, and adjudication. The remedy is to reconstruct the workflow via task decoupling and dynamic multi-round exploration. To this end, we propose SEMA-RAG, a Self-Evolving Multi-Agent RAG framework for medical question answering, which assigns these roles to three specialist agents: the Interpreter Agent for clinical schema interpretation, the Explorer Agent for sufficiency-driven self-evolving retrieval, and the Arbiter Agent for evidence adjudication and answer selection. Across five benchmarks and five LLM backbones, SEMA-RAG improves the strongest baseline by +6.46 accuracy points on average, measured per backbone.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。