多智能体系统通过记忆与反思提升医疗问答的准确性与可信度。
Adaptive Memory and Reflection Multi-Agent System for Medical Question Answering
- 分角色智能体搭配专用记忆与反思机制，动态调整推理路径。
- 在MedQA和MedMCQA上表现优于多个基线模型，准确率显著提升。
- 适合医疗AI开发、临床辅助决策等需要高可信度的场景。
精准且负责任的医疗问答对医疗健康至关重要，复杂病例需依赖事实知识与细致推理。现有医疗QA系统多基于单智能体架构与静态检索，缺乏适应性、持续记忆与结构化决策能力。本文提出自适应记忆与反思（AMR）多智能体系统，通过专业化智能体结合专用记忆与基于反思的反馈，实现相关历史案例的动态检索与推理优化。系统根据问题复杂度引导至独立、协作或升级工作流，并通过共识与伦理审查模块保障推理一致性与安全性。在MedQA和MedMCQA上的评估显示，该系统性能优于多个基线模型。消融实验表明，融合智能体专属记忆、反思机制与外部检索可获得最佳效果。结果表明，结构化记忆与反馈机制对构建更可信医疗智能体具有重要潜力。代码已公开于https://github.com/mm-air/AMR-Agent。
原文摘要 · Abstract (English)
Accurate and responsible medical question answering (QA) is important in healthcare, where complex cases require factual knowledge and nuanced reasoning. Existing medical QA systems, typically based on single-agent architectures and static retrieval, often lack adaptability, persistent memory, and structured decision-making. This work introduces an adaptive memory and reflection (AMR) agentic system, a multi-agent framework in which specialized agents use dedicated memory and reflection-based feedback to retrieve relevant prior cases and improve subsequent reasoning. Complexity assessment routes questions through solo, collaborative, or escalated workflows, while consensus and ethical overseer modules support reasoning consolidation and output review. Evaluation on MedQA and MedMCQA demonstrates strong performance compared with several baselines. Ablation studies show that combining agent-specific memory, reflection, and external retrieval yields the strongest performance. These findings highlight the potential of structured memory and feedback for developing more trustworthy medical agents. The source code is publicly available at https://github.com/mm-air/AMR-Agent.
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。