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

Pradeep Murugesan; Luoxiao Yang; Xueli Chen; Xinqi Fan

cs.AIAug 19, 2026

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

Authors: Pradeep Murugesan, Luoxiao Yang, Xueli Chen, Xinqi Fan

Organizations: School of Computing and Mathematics, Manchester Metropolitan University, UK · Electrical and Computer Engineering, Technion – Israel Institute of Technology, Israel · School of Science and Technology, Hong Kong Metropolitan University, Hong Kong SAR

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.

Figures & tables

Fig. 1: Pipeline of the adaptive memory and reflection (AMR) agentic system, including complexity assessment, dynamic routing, collaborative reasoning, memory, feedback, and post-generation safety screening.

Agent Node	Input	Output / Function
Moderator	User question	Assesses complexity
Recruiter	Complexity, question	Allocates agents
General Practitioner	Question	Single-agent reasoning
Collaborative Agents	Question	Multi-agent reasoning
Initial Report Agent	Question	Draft report
Review/Refine Agent	Report	Improves report

TABLE I: Roles and Responsibilities of AMR Agents

	MedQA	MedMCQA
Origin	USMLE (US)	AIIMS/NEET (India)
Questions	$\sim$ 12,700	$\sim$ 194,000
Format	Clinical vignette	Multiple-choice
Specialties	21+	21+
Reasoning	High	Mixed
Explanations	Partial	Full

TABLE II: Summary of Utilized Medical QA Datasets

Function	AMR	MDAgent	Debate	MedAgent	ReConcile
Multiple Roles	✓	✓	✓	✓	✓
Early Stopping	✓	✓	✓	✓	–
Refinement	✓	✓	✓	✓	–
Complexity Check	✓	✓	–	–	–
Multi-party Chat	✓	✓	✓	–	–
Conversation Pattern	Flexible	Flexible	Static	Static	Static

TABLE III: Comparison of Functions Across Multi-Agent Methods

Config	Mem	FB	RAG	MedQA	MedMCQA
Baseline	–	–	–	80%	78%
Feedback	–	✓	–	82%	80.4%
Memory	✓	–	–	86%	82%
AMR w/o RAG	✓	✓	–	90%	87.4%
AMR	✓	✓	✓	93.2%	90.0%

TABLE IV: Ablation studies.

Method	MedQA	MedMCQA
GPT-4	86.1%	73.7%
Human	87.0%	90.0%
MDAgents	86.5%	73.7%
MedAgents	83.0%	70.0%
AMR	93.2%	90.0%

TABLE V: Comparison with Other Methods

Fig. 2: Accuracies across different question complexity levels.

Panel of Figure 8 — Fig. 3: Qualitative analysis of the proposed AMR system. (a) A positive case showing correct and consistent reasoning with adaptive memory and reflection support. (b) A negative case showing an error instance used for reflection-driven feedback and future refinement.

Medical QA

Medical question answering develops and evaluates AI systems that answer clinical, patient-facing, and health-information questions.

See all 84 papers

SEMA-RAG: A Self-Evolving Multi-Agent Retrieval-Augmented Generation Framework for Medical Reasoning
May 16, 2026Yongfeng Huang, Ruiying Chen, James ChengRetrieval-Augmented Generation Healthcare
CSE, The Chinese University of Hong Kong · Wuhan University of Technology
Let Large Language Models Judge Each Other: Multi-Agent Peer-Reviewed Reasoning for Medical Question Answering
Jun 13, 2026Zaifu Zhan, Shuang Zhou, Rui ZhangMulti-Agent LLM Systems LLM Answer Verification
Department of Electrical and Computer Engineering, University of Minnesota, 200 Union St SE, 55455, Minneapolis, MN, United States · Division of Computational Health Sciences, Department of Surgery, University of Minnesota, 420 Delaware St SE, 55455, Minneapolis, MN, United States
MSM-Mem: A Universal Medical Structured Multimodal Memory Framework for Medical AI Agents
Aug 22, 2026Md Asaduzzaman Jabin, Khoa Le, Lin Zhao +1Medical AI Agents LLM Agent Memory
University of Georgia, Athens, GA, USA · New Jersey Institute of Technology, Newark, NJ, USA

May 16, 2026J/K move · Enter open · S save

SEMA-RAG: A Self-Evolving Multi-Agent Retrieval-Augmented Generation Framework for Medical Reasoning

Yongfeng Huang, Ruiying Chen, James Cheng

CSE, The Chinese University of Hong Kong · Wuhan University of Technology

Retrieval-Augmented Generation Healthcare Clinical QA Agentic RAG Medical Reasoning

Open paper AskPDF arXiv

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.

Abstract

Medical QA

Explore similar work

SEMA-RAG: A Self-Evolving Multi-Agent Retrieval-Augmented Generation Framework for Medical Reasoning

Let Large Language Models Judge Each Other: Multi-Agent Peer-Reviewed Reasoning for Medical Question Answering

MSM-Mem: A Universal Medical Structured Multimodal Memory Framework for Medical AI Agents