Adaptive Memory and Reflection Multi-Agent System for Medical Question Answering
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 14 of its 30 references that are in the map. First posted on arXiv 19 Aug 2026.
Builds on
14 of 30 references.
References · 14
- 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,784
- 2020What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Examscited by 1,356
- 2022MedMCQA : A Large-scale Multi-Subject Multi-Choice Dataset for Medical domain Question Answeringcited by 543
- 2023MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoningcited by 316
- 2023ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMscited by 309
- 2025Agentic Retrieval-Augmented Generation: A Survey on Agentic RAGcited by 249
- 2024MDAgents: An Adaptive Collaboration of LLMs for Medical Decision-Makingcited by 163
- 2021Biomedical Question Answering: A Survey of Approaches and Challengescited by 46
- 2024Rationale-Guided Retrieval Augmented Generation for Medical Question Answeringcited by 41
- 2024KG4Diagnosis: A Hierarchical Multi-Agent LLM Framework with Knowledge Graph Enhancement for Medical Diagnosiscited by 26
- 2024Medchain: Bridging the Gap Between LLM Agents and Clinical Practice with Interactive Sequencecited by 17
- 2024Large Language Models and User Trust: Consequence of Self-Referential Learning Loop and the Deskilling of Healthcare Professionalscited by 13
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026Let LLMs Judge Each Other: Multi-Agent Peer-Reviewed Reasoning for Medical Question Answering
- 2026MediHive: A Decentralized Agent Collective for Medical Reasoning
- 2026From Conflict to Consensus: Boosting Medical Reasoning via Multi-Round Agentic RAG
- 2026SEMA-RAG: A Self-Evolving Multi-Agent Retrieval-Augmented Generation Framework for Medical Reasoning
- 2025MedLA: A Logic-Driven Multi-Agent Framework for Complex Medical Reasoning with Large Language Models
- 2026A Multi-Agent Framework for Medical AI: Leveraging Fine-Tuned GPT, LLaMA, and DeepSeek R1 for Evidence-Based and Bias-Aware Clinical Query Processing
- 2024LLM-MedQA: Enhancing Medical Question Answering through Case Studies in Large Language Models
- 2025Talk Before You Retrieve: Agent-Led Discussions for Better RAG in Medical QA