A Self-Evolving Framework for Multi-Agent Medical Consultation Based on Large Language Models
Abstract
We propose a multi-agent approach (SeM-Agents) based on large language models for medical consultations. This framework incorporates various doctor roles and auxiliary roles, with agents communicating through natural language. Using a residual structure, the system conducts multi-round medical consultations based on the patient’s treatment background and symptoms. In the final summary and output stage of the consultation, it utilizes two experience databases—the Correct Consultation Experience Database and the Chain of Thought (CoT) Experience Database—which evolve with accumulated experience during consultations. This evolution drives the framework’s self-improvement, significantly enhancing the rationality and accuracy of the consultations. To ensure that the conclusions are safe, reliable, and aligned with human values, the final decisions undergo a safety review before being provided to the patient. This framework achieved accuracy rates of 89.2% and 83.1% on the MedQA and PubMedQA datasets, respectively.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Existing multi-LLM frameworks rely on fixed mechanisms such as consensus voting or stepwise reasoning to aggregate independent LLM outputs but lack dynamic, debate-style interaction essential for robust reasoning.
“Prior studies rely on fixed mechanisms such as consensus voting8,9 or stepwise reasoning10 to aggregate independent LLM outputs but lack dynamic, debate-style interaction essential for robust reasoning.”
From Model confrontation and collaboration: A debate intelligence framework for enhancing medical reasoning in large language models (2026) · cites this paper as [9]
Several multi-LLM frameworks (MedAgents, MDTeamGPT, MDAgents) employ role specialization to enhance accuracy.
“Several multi-LLM frameworks, such as MedAgents,8 MDTeamGPT,9 and MDAgents,34 employ role specialization (e.g., proposer, reviewer, simulated expert, or specialty-specific expert pools) to enhance accuracy.”
From Model confrontation and collaboration: A debate intelligence framework for enhancing medical reasoning in large language models (2026) · cites this paper as [9]
Cites
LLaMA: Open and Efficient Foundation Language Models
Touvron, H., Lavril, T., Izacard, G., Martinet, X., Lachaux, M.-A., Lacroix, T., Rozière, B., Goyal, N., Hambro, E., Azhar, F., et al. (2023) · arXiv · doi:10.48550/arxiv.2302.13971 · Cited by 4,602 · see citing works
Generative Agents: Interactive Simulacra of Human Behavior
Park, J. S., O'Brien, J., Cai, C. J., Morris, M. R., Liang, P., & Bernstein, M. S. (2023) · Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology · doi:10.1145/3586183.3606763 · Cited by 2,187 · see citing works
ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All ToolsPreprint
Zeng, A.-H., Xu, B., Wang, B.-W., Zhang, C., Yin, D., Rojas, D., Feng, G., Zhao, H., Lai, H., Yu, H., et al. (2024) · arXiv.org · doi:10.48550/arxiv.2406.12793 · Cited by 1,884 · see citing works
Self-citationJin, D., Pan, E., Oufattole, N., Weng, W.-H., Fang, H., & Szolovits, P. (2021) · Applied Sciences · doi:10.3390/app11146421 · Cited by 718 · see citing works
PubMedQA: A Dataset for Biomedical Research Question Answering
Jin, Q., Dhingra, B., Liu, Z., Cohen, W., & Lu, X. (2019) · Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · doi:10.18653/v1/d19-1259 · Cited by 685 · see citing works
ChatDev: Communicative Agents for Software Development
Qian, C., Liu, W., Liu, H., Chen, N., Dang, Y., Li, J., Yang, C., Chen, W., Su, Y., Cong, X., et al. (2024) · Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2024.acl-long.810 · Cited by 490 · see citing works
MemoryBank: Enhancing Large Language Models with Long-Term Memory
Zhong, W., Guo, L., Gao, Q., Ye, H., & Wang, Y. (2023) · arXiv · doi:10.48550/arxiv.2305.10250 · Cited by 253 · see citing works
MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework
Hong, S., Zhuge, M., Chen, J., Zheng, X., Cheng, Y., Zhang, C., Wang, J., Wang, Z., Yau, S. K. S., Lin, Z., et al. (2023) · arXiv · doi:10.48550/arxiv.2308.00352 · Cited by 214 · cited 1× · see citing works
“MetaGPT [17] assigns agents roles within a software company and encodes Standard Operating Procedures (SOPs), demonstrating how to integrate agents’ expertise to efficiently complete tasks.”
Can Generalist Foundation Models Outcompete Special-Purpose Tuning? Case Study in Medicine
Nori, H., Lee, Y. T., Zhang, S., Carignan, D., Edgar, R., Fusi, N., King, N., Larson, J., Li, Y., Liu, W., et al. (2023) · arXiv · doi:10.48550/arxiv.2311.16452 · Cited by 178 · see citing works
Expel: LLM agents are experiential learners
Zhao, A., Huang, D., Xu, Q., Lin, M., Liu, Y.-J., & Huang, G. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i17.29936 · Cited by 153 · see citing works
Med-HALT: Medical Domain Hallucination Test for Large Language Models
Pal, A., Umapathi, L. K., & Sankarasubbu, M. (2023) · Proceedings of the 27th Conference on Computational Natural Language Learning (CoNLL) · doi:10.18653/v1/2023.conll-1.21 · Cited by 152 · see citing works
MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoning
Tang, X., Zou, A., Zhang, Z., Li, Z., Zhao, Y., Zhang, X., Cohan, A., & Gerstein, M. (2024) · Findings of the Association for Computational Linguistics ACL 2024 · doi:10.18653/v1/2024.findings-acl.33 · Cited by 133 · see citing works
DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
DeepSeek-AI, Liu, A., Feng, B., Wang, B., Wang, B., Liu, B., Zhao, C., Dengr, C., Ruan, C., Dai, D., et al. (2024) · arXiv · doi:10.48550/arxiv.2405.04434 · Cited by 109 · see citing works
Self-citationImproving Factuality and Reasoning in Language Models through Multiagent Debate
Du, Y., Li, S., Torralba, A., Tenenbaum, J. B., & Mordatch, I. (2023) · arXiv · doi:10.48550/arxiv.2305.14325 · Cited by 96 · see citing works
Cognitive Mirage: A Review of Hallucinations in Large Language Models
Ye, H., Liu, T., Zhang, A., Hua, W., & Jia, W. (2023) · arXiv · doi:10.48550/arxiv.2309.06794 · Cited by 61 · see citing works
Agent Hospital: A Simulacrum of Hospital with Evolvable Medical Agents
Li, J., Lai, Y., Li, W., Ren, J., Zhang, M., Kang, X., Wang, S., Li, P., Zhang, Y.-Q., Ma, W., et al. (2024) · arXiv · doi:10.48550/arxiv.2405.02957 · Cited by 46 · see citing works
DISC-MedLLM: Bridging General Large Language Models and Real-World Medical ConsultationPreprint
Bao, Z., Chen, W., Xiao, S., Ren, K., Wu, J., Zhong, C., Peng, J., Huang, X., & Wei, Z. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2308.14346 · Cited by 26 · see citing works
AlpaCare:Instruction-tuned Large Language Models for Medical ApplicationPreprint
Zhang, X., Tian, C., Yang, X., Chen, L.-C., Li, Z., & Petzold, L. R. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2310.14558 · Cited by 21 · see citing works
Self-citationSelfEvolve: A Code Evolution Framework via Large Language ModelsPreprint
Jiang, S., Wang, Y., & Wang, Y. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2306.02907 · Cited by 18 · see citing works
Training Socially Aligned Language Models on Simulated Social Interactions
Liu, R., Yang, R., Jia, C., Zhang, G., Zhou, D., Dai, A. M., Yang, D., & Vosoughi, S. (2023) · arXiv · doi:10.48550/arxiv.2305.16960 · Cited by 18 · see citing works
Experiential Co-Learning of Software-Developing Agents
Qian, C., Dang, Y., Li, J., Liu, W., Xie, Z., Wang, Y., Chen, W., Yang, C., Cong, X., Che, X., et al. (2024) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2024.acl-long.305 · Cited by 15 · see citing works
Turn-Taking and Backchannel Prediction with Acoustic and Large Language Model Fusion
Wang, J., Chen, L., Khare, A., Raju, A., Dheram, P., He, D., Wu, M., Stolcke, A., & Ravichandran, V. (2024) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp48485.2024.10447196 · Cited by 12 · see citing works
Multi-Modal GPT-4 Aided Action Planning and Reasoning for Self-driving Vehicles
Chi, F., Wang, Y., Nasiopoulos, P., & Leung, V. C. M. (2024) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp48485.2024.10446745 · Cited by 9 · see citing works
Scaling Large Language Model-based Multi-Agent Collaboration
Qian, C., Xie, Z., Wang, Y., Liu, W., Zhu, K., Xia, H., Dang, Y., Du, Z., Chen, W., Yang, C., et al. (2024) · arXiv · doi:10.48550/arxiv.2406.07155 · Cited by 8 · see citing works
Are More LLM Calls All You Need? Towards Scaling Laws of Compound Inference Systems
Chen, L., Davis, J. Q., Hanin, B., Bailis, P., Stoica, I., Zaharia, M., & Zou, J. (2024) · arXiv · doi:10.48550/arxiv.2403.02419 · Cited by 7 · see citing works
Multi-Agent Collaboration via Cross-Team OrchestrationPreprint
Du, Z., Qian, C., Liu, W., Xie, Z., Wang, Y., Qiu, R., Dang, Y., Chen, W., Yang, C. H., Tian, Y., et al. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2406.08979 · Cited by 5 · see citing works
SEGLLM: Topic-Oriented Call Segmentation Via LLM-Based Conversation Synthesis
Malkiel, I., Alon, U., Yehuda, Y., Keren, S., Barkan, O., Ronen, R., & Koenigstein, N. (2024) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp48485.2024.10446156 · Cited by 4 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Gao, H.-A., Geng, J., Hua, W., Hu, M., Juan, X., Liu, H., Liu, S., Qiu, J., Qi, X., Wu, Y., et al. (2025) · arXiv · doi:10.48550/arxiv.2507.21046 · Cited by 3 · see citing works
MDTeamGPT: Mitigating Context Collapse and Enabling Self-Evolution in Medical Multi-Agent Reasoning
Chen, K., Li, X., Yang, T., Wang, H., Yang, G., Huo, J., & Gao, Y. (2026) · Findings of the Association for Computational Linguistics: ACL 2026 · doi:10.18653/v1/2026.findings-acl.1427 · Cited by 1 · see citing works
Self-citationEnhancing Medical Question Answering via a Multi-Agent Debate Framework
Lu, D., Jiang, V., Wang, S., Zhu, M., & Zhai, S. (2026) · IEEE Annual Computing and Communication Workshop and Conference (CCWC) · doi:10.1109/ccwc67433.2026.11393824
Self-Evolving Diagnostic Framework based Gated Residual Adapters and OpenClaw-Based Medical Agents
Feng, S., & Su, P. (2026) · International Journal of Computer Science and Information Technology · doi:10.62051/ijcsit.v8n4.01
Global and Coalition Cognition Graph Modeling for Interpretable Multiagent Reinforcement Learning
Wu, X., Zhu, Y., Dong, D., Wei, J., & Chen, C. (2026) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2026.3703166
MDTace: Agentic Context Engineering for Multi-disciplinary Team Medical Consultation
Chen, K., & Gao, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-3403-5_6
Self-citationMedMentor: Teacher-Student Collaboration with Decoupled Experience for Clinical Diagnosis
Chen, K., & Gao, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-3403-5_7
Self-citationVatsal, S., Dubey, H., & Bajaj, A. (2026) · IEEE Access · doi:10.1109/access.2026.3720396
- Authors
- Chen, K., Qi, J., Huo, J., Tian, P., Meng, F., Yang, X., & Gao, Y.
- Affiliations
- Nanjing University (CN)
- China Mobile (China) (CN)
- Shanghai University (CN)
- China Mobile Research Institute (CN)
- Venue
- ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
- Publisher
- IEEE
- Published
- 2025-04-06
- Pages
- 1-5
- ISSN
- 1520-6149 (ISSN-L)
- OpenAlex
- W4408352269
- Cited by
- 6
- References
- 27
- Citations by year
- 2026: 6
- FWCI
- 6.28
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE International Conference on Acoustics Speech and Signal Processing (publishedVersion)
- Funders
- Nanjing University
- National Natural Science Foundation of China
- Natural Science Foundation of Jiangsu Province
- Topics
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
- Keywords
- multi-agent systems, large language models, medical consultation, self-evolving agents, chain-of-thought, multi-turn dialogue, safety review, MedQA, PubMedQA
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
