Paper Detail

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

Pradeep Murugesan, Luoxiao Yang, Xueli Chen, Xinqi Fan

arxiv Score 21.3

Published 2026-08-19 · First seen 2026-08-20

Research Track A · General AI

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.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
now
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@article{murugesan2026adaptive,
  title = {Adaptive Memory and Reflection Multi-Agent System for Medical Question Answering},
  author = {Pradeep Murugesan and Luoxiao Yang and Xueli Chen and Xinqi Fan},
  year = {2026},
  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 fe},
  url = {https://arxiv.org/abs/2608.19029},
  keywords = {cs.AI, cs.CL, cs.MA},
  eprint = {2608.19029},
  archiveprefix = {arXiv},
}

Metadata

{}