# MDTeamGPT: A Self-Evolving LLM-based Multi-Agent Framework for Multi-Disciplinary Team Medical Consultation

arXiv: https://arxiv.org/abs/2503.13856 · HTML: https://mlsanity.com/paper/2503.13856/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use.
- Builds on 24 of its 37 references that are in the map.
- First posted on arXiv 18 Mar 2025.

## Placed in

- LLM agents and tool use / [Medical and scientific domain agents](https://mlsanity.com/agents/medical-and-scientific-domain-agents/)
- Synthetic data and self-improvement for LLMs / [Medical synthetic data and agents](https://mlsanity.com/synth/medical-synthetic-data-and-agents/)

## Builds on (most cited first, 24 of 24)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams](https://mlsanity.com/paper/2009.13081/) (2020)
- [PubMedQA: A Dataset for Biomedical Research Question Answering](https://mlsanity.com/paper/1909.06146/) (2019)
- [ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools](https://mlsanity.com/paper/2406.12793/) (2024)
- [ChatDev: Communicative Agents for Software Development](https://mlsanity.com/paper/2307.07924/) (2023)
- [ExpeL: LLM Agents Are Experiential Learners](https://mlsanity.com/paper/2308.10144/) (2023)
- [Evaluating Very Long-Term Conversational Memory of LLM Agents](https://mlsanity.com/paper/2402.17753/) (2024)
- [Can Generalist Foundation Models Outcompete Special-Purpose Tuning? Case Study in Medicine](https://mlsanity.com/paper/2311.16452/) (2023)
- [MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoning](https://mlsanity.com/paper/2311.10537/) (2023)
- [Scaling Large Language Model-based Multi-Agent Collaboration](https://mlsanity.com/paper/2406.07155/) (2024)
- [AgentClinic: a multimodal agent benchmark to evaluate AI in simulated clinical environments](https://mlsanity.com/paper/2405.07960/) (2024)
- [Agent Hospital: A Simulacrum of Hospital with Evolvable Medical Agents](https://mlsanity.com/paper/2405.02957/) (2024)
- [Hello Again! LLM-powered Personalized Agent for Long-term Dialogue](https://mlsanity.com/paper/2406.05925/) (2024)
- [Training Socially Aligned Language Models on Simulated Social Interactions](https://mlsanity.com/paper/2305.16960/) (2023)
- [LLM Discussion: Enhancing the Creativity of Large Language Models via Discussion Framework and Role-Play](https://mlsanity.com/paper/2405.06373/) (2024)
- [Experiential Co-Learning of Software-Developing Agents](https://mlsanity.com/paper/2312.17025/) (2023)
- [MEDCO: Medical Education Copilots Based on A Multi-Agent Framework](https://mlsanity.com/paper/2408.12496/) (2024)
- [Multi-Agent Collaboration via Cross-Team Orchestration](https://mlsanity.com/paper/2406.08979/) (2024)
- [Iterative Experience Refinement of Software-Developing Agents](https://mlsanity.com/paper/2405.04219/) (2024)
- [Advancing Healthcare Automation: Multi-Agent System for Medical Necessity Justification](https://mlsanity.com/paper/2404.17977/) (2024)

## Built on by (most cited first, 26 of 26)

- [A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence](https://mlsanity.com/paper/2507.21046/) (2025)
- [MedSentry: Understanding and Mitigating Safety Risks in Medical LLM Multi-Agent Systems](https://mlsanity.com/paper/2505.20824/) (2025)
- [EvoClinician: A Self-Evolving Agent for Multi-Turn Medical Diagnosis via Test-Time Evolutionary Learning](https://mlsanity.com/paper/2601.22964/) (2026)
- [Reasoning LLMs in the Medical Domain: A Literature Survey](https://mlsanity.com/paper/2508.19097/) (2025)
- [Mediator-Guided Multi-Agent Collaboration among Open-Source Models for Medical Decision-Making](https://mlsanity.com/paper/2508.05996/) (2025)
- [Self-Improvement of Large Language Models: A Technical Overview and Future Outlook](https://mlsanity.com/paper/2603.25681/) (2026)
- [Perspectra: Choosing Your Experts Enhances Critical Thinking in Multi-Agent Research Ideation](https://mlsanity.com/paper/2509.20553/) (2025)
- [MeDxAgent: Multi-Agent Consultation for Interactive Medical Diagnosis](https://mlsanity.com/paper/2606.03416/) (2026)
- [A Knowledge-driven Adaptive Collaboration of LLMs for Enhancing Medical Decision-making](https://mlsanity.com/paper/2509.14998/) (2025)
- [CubeBench: Diagnosing Interactive, Long-Horizon Spatial Reasoning Under Partial Observations](https://mlsanity.com/paper/2512.23328/) (2025)
- [Improving the Safety and Trustworthiness of Medical AI via Multi-Agent Evaluation Loops](https://mlsanity.com/paper/2601.13268/) (2026)
- [MedMASLab: A Unified Orchestration Framework for Benchmarking Multimodal Medical Multi-Agent Systems](https://mlsanity.com/paper/2603.09909/) (2026)
- [TAGS: A Test-Time Generalist-Specialist Framework with Retrieval-Augmented Reasoning and Verification](https://mlsanity.com/paper/2505.18283/) (2025)
- [MedCoG: Maximizing LLM Inference Density in Medical Reasoning via Meta-Cognitive Regulation](https://mlsanity.com/paper/2602.07905/) (2026)
- [The Path to Self-Evolving Clinical Systems: Scaling Medical Agents from Assistance to Autonomy](https://mlsanity.com/paper/2607.11175/) (2026)
- [Grammar-Guided Evolutionary Search for Discrete Prompt Optimisation](https://mlsanity.com/paper/2507.10326/) (2025)
- [Agentic AI in Healthcare & Medicine: A Seven-Dimensional Taxonomy for Empirical Evaluation of LLM-based Agents](https://mlsanity.com/paper/2602.04813/) (2026)
- [EMR: Self-Evolving Medical Multi-Agent System via Experience Mining and Reuse](https://mlsanity.com/paper/2609.15161/) (2026)
- [Segregation and Context Aggregation Network for Real-time Cloud Segmentation](https://mlsanity.com/paper/2504.14178/) (2025)
- ["Do I Trust the AI?" Towards Trustworthy AI-Assisted Diagnosis: Understanding User Perception in LLM-Supported Reasoning](https://mlsanity.com/paper/2601.19540/) (2026)
- [FetalAgents: A Multi-Agent System for Fetal Ultrasound Image and Video Analysis](https://mlsanity.com/paper/2603.09733/) (2026)
- [Agents that Matter: Optimizing Multi-Agent LLMs via Removal-Based Attribution](https://mlsanity.com/paper/2605.27621/) (2026)
- [Traj-Evolve: A Self-Evolving Multi-Agent System for Patient Trajectory Modeling in Lung Cancer Early Detection](https://mlsanity.com/paper/2606.02812/) (2026)
- [Let LLMs Judge Each Other: Multi-Agent Peer-Reviewed Reasoning for Medical Question Answering](https://mlsanity.com/paper/2606.15419/) (2026)
- [SSE-Bio: A Structured Self-Evolving Agent with Agentic Retrieval Policy for Multi-Hop Biomedical Reasoning](https://mlsanity.com/paper/2608.22132/) (2026)
- [HEM-Med: A Hierarchical Agentic Memory Framework for Safe Multi-Center Medication Recommendation](https://mlsanity.com/paper/2610.20191/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) have made significant progress in various fields. However, challenges remain in Multi-Disciplinary Team (MDT) medical consultations. Current research enhances reasoning through role assignment, task decomposition, and accumulation of medical experience. Multi-role collaboration in MDT consultations often results in excessively long dialogue histories. This increases the model's cognitive burden and degrades both efficiency and accuracy. Some methods only store treatment histories. They do not extract effective experience or reflect on errors. This limits knowledge generalization and system evolution. We propose a multi-agent MDT medical consultation framework based on LLMs to address these issues. Our framework uses consensus aggregation and a residual discussion structure for multi-round consultations. It also employs a Correct Answer Knowledge Base (CorrectKB) and a Chain-of-Thought Knowledge Base (ChainKB) to accumulate consultation experience. These mechanisms enable the framework to evolve and continually improve diagnosis rationality and accuracy. Experimental results on the MedQA and PubMedQA datasets demonstrate that our framework achieves accuracies of 90.1% and 83.9%, respectively, and that the constructed knowledge bases generalize effectively across test sets from both datasets.