Adaptive Memory and Reflection Multi-Agent System for Medical Question Answering

2026-08-19

AI Summary

本文针对现有医疗问答系统缺乏适应性、持久记忆和结构化决策的问题，提出了一种基于多代理的自适应记忆与反思系统，通过专门的记忆和反馈机制提高复杂案例处理能力。

Abstract

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.

Problem

• medical question answering
• adaptive memory
• reflection
• multi-agent system
• structured decision-making

Innovation

• adaptive memory and reflection
• multi-agent system
• medical question answering
• complexity assessment
• consensus module