CoChat
Sign Up
Cited by 3Artificial Intelligence in Healthcare and EducationArtificial Intelligence in HealthcareMachine Learning in Healthcare

ClinicalAgents: Multi-Agent Orchestration for Clinical Decision Making with Dual-Memory

Open access
Ge, Zhuohan, Li, Haoyang, Wang, Yubo, Hu, Nicole, Zhang, Chen Jason, Li, Qing·2026·Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2
DOI 10.1145/3770855.3818931
Open this paper in CoChat — free account

Abstract

While Large Language Models (LLMs) have demonstrated potential in healthcare, they often struggle with the complex, non-linear reasoning required for accurate clinical diagnosis. Existing methods typically rely on static, linear mappings from symptoms to diagnoses, failing to capture the iterative, hypothesis-driven reasoning inherent in human clinicians. To bridge this gap, we introduce ClinicalAgents, a novel multi-agent framework designed to simulate the cognitive workflow of expert clinicians. Unlike rigid sequential chains, ClinicalAgents employs a dynamic orchestration mechanism modeled as a Monte Carlo Tree Search (MCTS) process. This allows an orchestrator to iteratively generate hypotheses, actively verify evidence, and trigger backtracking when critical information is missing. The foundation of this framework is a Dual-Memory architecture: a mutable working memory that maintains the evolving patient state for context-aware reasoning, and a static experience memory that retrieves clinical guidelines and historical cases via an active feedback loop. Extensive experiments demonstrate that ClinicalAgents achieves the best performance among evaluated baselines, significantly enhancing both diagnostic accuracy and explainability compared to strong single-agent and multi-agent baselines. Our code is released at https://github.com/ZhuohanGe/ClinicalAgents-Code.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1145/3770855.3818931

Cites

0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

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?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

The publisher hasn’t deposited this paper’s reference list.

Research works printed but not linked: 37

  1. [3][3] Cameron B Browne, Edward Powley, et al. 2012. A survey of Monte Carlo tree search methods. IEEE Transactions on Computational Intelligence and AI in Games 4, 1 (2012), 1-43. -
  2. [4][4] Hanjie Chen, Zhouxiang Fang, Yash Singla, and Mark Dredze. 2025. Benchmarking large language models on answering and explaining challenging medical questions. In Proceedings of the 2025 Conference of NAACL. 3563-3599. -
  3. [6][6] Justin Chen, Swarnadeep Saha, and Mohit Bansal. 2024. ReConcile: Roundtable conference improves reasoning via consensus among diverse LLMs. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 7066-7085. -
  4. [7][7] Zhe Chen, Jiannan Wu, et al. 2024. InternVL: Scaling up vision foundation models and aligning for generic visual-linguistic tasks. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 24185-24198. -
  5. [8][8] Shehzaad Dhuliawala, Mojtaba Komeili, Jing Xu, Roberta Raileanu, Xian Li, Asli Celikyilmaz, and Jason Weston. 2024. Chain-of-verification reduces hallucination in large language models. In Findings of the association for computational linguistics: ACL 2024. 3563-3578. -
  6. [9][9] Quang Hung Duong, To Nhu Pham, Lorenna Reynolds, Yan Yeap, Steven Walker, and Kayley Lyons. 2023. A scoping review of therapeutic reasoning process research. Advances in Health Sciences Education 28, 4 (2023), 1289-1310. -
  7. [10][10] Arthur S Elstein and Alan Schwarz. 2002. Clinical problem solving and diagnostic decision making: selective review of the cognitive literature. BMJ 324, 7339 (2002), 729-732. -
  8. [13][13] Ali Hatamizadeh, Yucheng Tang, et al. 2022. UNETR: Transformers for 3D medical image segmentation. In Proceedings of the IEEE/CVF winter conference on applications of computer vision. 574-584. -
  9. [15][15] Joy Higgs, Gail M Jensen, Stephen Loftus, Franziska V Trede, and Sandra Grace. 2024. Clinical reasoning in the health professions. Elsevier Health Sciences. -
  10. [16][16] Di Jin, Eileen Pan, et al. 2021. What disease does this patient have? A large-scale open domain question answering dataset from medical exams. Applied Sciences 11, 14 (2021), 6421. -
  11. [17][17] Qiao Jin, Bhuwan Dhingra, Zhengping Liu, William Cohen, and Xinghua Lu. 2019. PubMedQA: A dataset for biomedical research question answering. In Proceedings of the 2019 conference on EMNLP-IJCNLP. 2567-2577. -
  12. [18][18] Lars Benedikt Kaesberg, Jonas Becker, Jan Philip Wahle, Terry Ruas, and Bela Gipp. 2025. Voting or consensus? Decision-making in multi-agent debate. arXiv preprint arXiv:2502.19130 (2025). - · arXiv
  13. [19][19] Yubin Kim, Chanwoo Park, et al. 2024. MDAgents: An adaptive collaboration of LLMs for medical decision-making. Advances in Neural Information Processing Systems 37 (2024), 79410-79452. -
  14. [21][21] Yikuan Li, Mohammad Mamouei, et al. 2022. Hi-BEHRT: hierarchical transformerbased model for accurate prediction of clinical events using multimodal longitudinal electronic health records. IEEE Journal of Biomedical and Health Informatics 27, 2 (2022), 1106-1117. -
  15. [22][22] Jie Liu, Wenxuan Wang, et al. 2025. Medchain: Bridging the gap between llm agents and clinical practice with interactive sequence. Advances in Neural Information Processing Systems 38. -
  16. [23][23] Wenge Liu, Jianheng Tang, et al. 2022. MedDG: An entity-centric medical consultation dataset for entity-aware medical dialogue generation. In CCF International Conference on Natural Language Processing and Chinese Computing (NLPCC). Springer, 447-459. -
  17. [24][24] Junyu Luo, Muchao Ye, Cao Xiao, and Fenglong Ma. 2020. HiTANet: Hierarchical time-aware attention networks for risk prediction on electronic health records. In Proceedings of the 26th ACM SIGKDD international conference on knowledge discovery & data mining. 647-656. -
  18. [25][25] Munib Mesinovic, Peter Watkinson, and Tingting Zhu. 2025. Explainability in the age of large language models for healthcare. Communications Engineering 4, 1 (2025), 128. -
  19. [29][29] Vimla L Patel and Guy J Groen. 1986. Knowledge based solution strategies in medical reasoning. Cognitive Science 10, 1 (1986), 91-116. -
  20. [30][30] Qi Peng, Jialin Cui, et al. 2025. Tree-of-reasoning: Towards complex medical diagnosis via multi-agent reasoning with evidence tree. In Proceedings of the 33rd ACM International Conference on Multimedia. 1744-1753. -
  21. [31][31] Martin L Puterman. 1990. Markov decision processes. Handbooks in operations research and management science 2 (1990), 331-434. -
  22. [32][32] Laila Rasmy, Yang Xiang, Ziqian Xie, Cui Tao, and Degui Zhi. 2021. Med-BERT: pretrained contextualized embeddings on large-scale structured electronic health records for disease prediction. NPJ Digital Medicine 4, 1 (2021), 86. -
  23. [34][34] David Silver, Aja Huang, et al. 2016. Mastering the game of Go with deep neural networks and tree search. Nature 529, 7587 (2016), 484-489. -
  24. [35][35] Karan Singhal, Tao Tu, et al. 2025. Toward expert-level medical question answering with large language models. Nature Medicine 31, 3 (2025), 943-950. -
  25. [36][36] Reed T Sutton, David Pincock, et al. 2020. An overview of clinical decision support systems: benefits, risks, and strategies for success. NPJ Digital Medicine 3, 1 (2020), 17. -
  26. [37][37] Xiangru Tang, Anni Zou, Zhuosheng Zhang, Ziming Li, Yilun Zhao, Xingyao Zhang, Arman Cohan, and Mark Gerstein. 2024. MedAgents: Large language models as collaborators for zero-shot medical reasoning. In Findings of the Association for Computational Linguistics: ACL 2024. 599-621. -
  27. [38][38] Jennifer Tiffen, Susan J Corbridge, and Lynda Slimmer. 2014. Enhancing clinical decision making: development of a contiguous definition and conceptual framework. Journal of Professional Nursing 30, 5 (2014), 399-405. -
  28. [39][39] Tao Tu, Mike Schaekermann, Anil Palepu, Khaled Saab, Jan Freyberg, Ryutaro Tanno, Amy Wang, Brenna Li, Mohamed Amin, Yong Cheng, et al. 2025. Towards conversational diagnostic artificial intelligence. Nature 642, 8067 (2025), 442-450. -
  29. [40][40] Yubo Wang, Haoyang Li, et al. 2025. AGRAG: Advanced graph-based retrievalaugmented generation for LLMs. arXiv preprint arXiv:2511.05549 (2025). - · arXiv
  30. [41][41] Zixiang Wang, Yinghao Zhu, et al. 2025. ColaCare: Enhancing electronic health record modeling through large language model-driven multi-agent collaboration. In Proceedings of the ACM on Web Conference 2025. 2250-2261. -
  31. [42][42] Jason Wei, Xuezhi Wang, et al. 2022. Chain-of-thought prompting elicits reasoning in large language models. Advances in Neural Information Processing Systems 35 (2022), 24824-24837. -
  32. [44][44] Qingyun Wu, Gagan Bansal, et al. 2024. AutoGen: Enabling next-gen LLM applications via multi-agent conversations. In First conference on language modeling. -
  33. [45][45] Yiqing Xie, Sheng Zhang, et al. 2024. DocLens: Multi-aspect fine-grained medical text evaluation. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 649-679. -
  34. [46][46] Shunyu Yao, Jeffrey Zhao, et al. 2023. ReAct: Synergizing reasoning and acting in language models. In International Conference on Learning Representations (ICLR). -
  35. [48][48] Kun-Hsing Yu, Andrew L Beam, and Isaac S Kohane. 2018. Artificial intelligence in healthcare. Nature Biomedical Engineering 2, 10 (2018), 719-731. -
  36. [49][49] Hongbo Zhang, Junying Chen, et al. 2023. HuatuoGPT: Towards taming language model to be a doctor. In Findings of the association for computational linguistics: EMNLP 2023. 10859-10885. -
  37. [50][50] Shuang Zhou, Jiashuo Wang, et al. 2025. Uncertainty-aware large language models for explainable disease diagnosis. npj Digital Medicine 8, 1 (2025), 690.

Cited by

Sorted by citations

Related

Authors
Ge, Z., Li, H., Wang, Y., Hu, N., Zhang, C. J., & Li, Q.
Affiliations
  • Hong Kong Polytechnic University (HK)
  • The Hong Kong University of Science and Technology, Hong Kong SAR, China
ORCID
Venue
Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2
Publisher
ACM
Published
2026-08-08
Pages
10969-10980
DOI
10.1145/3770855.3818931
OpenAlex
W7162804352
Cited by
2
References
0
Citations by year
2026: 2
FWCI
18.89
Type
conference paper
Language
en
Open access
Licence
Locations
  • ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) (publishedVersion, cc-by)
  • arXiv (Cornell University) (submittedVersion, cc-by)
  • arXiv (Cornell University) (cc-by)
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 › Artificial Intelligence › Machine Learning in Healthcare
Keywords
multi-agent systems, clinical decision-making, diagnosis, Monte Carlo tree search, working memory, hypothesis generation, backtracking, explainable AI, large language models in healthcare

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