发表机构
School of Computing and Mathematics, Manchester Metropolitan University; Electrical and Computer Engineering, Technion – Israel Institute of Technology; School of Science and Technology, Hong Kong Metropolitan University（曼彻斯特城市大学计算与数学学院; 以色列理工学院电气与计算机工程系; 香港都会大学科学与科技学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对现有医学问答系统缺乏适应性等问题，提出自适应记忆与反思多智能体框架，经MedQA等数据集验证，结合专用记忆等模块可提升性能，助力开发可信医学智能体。
AI 中文摘要
准确且负责任的医学问答（QA）在医疗领域至关重要，复杂病例需要事实性知识和精细推理。现有医学问答系统通常基于单智能体架构和静态检索，往往缺乏适应性、持久记忆和结构化决策。本研究提出自适应记忆与反思（AMR）智能体系统，这是一种多智能体框架，其中专门智能体使用专用记忆和基于反思的反馈来检索相关既往案例并改进后续推理。复杂度评估将问题路由至单智能体、协作或升级工作流，而共识和伦理监督模块支持推理整合与输出审查。在MedQA和MedMCQA上的评估显示，与多个基线相比性能强劲。消融研究表明，结合智能体专用记忆、反思和外部检索可产生最强性能。这些发现凸显了结构化记忆与反馈在开发更可信医学智能体方面的潜力。源代码可在此URL获取。
英文摘要
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.
CommentsAccepted by IEEE SMC 2026
