Agentic AI for Medicine
In Conjunction with the International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) 2025
September 23 or 27, 2025, Daejeon, South Korea
About
The field of medical AI has evolved from predictive AI to generative AI and is about to enter the era of agentic AI, poised for rapid growth in 2025. Unlike previous generations of AI, which passively execute human instructions and are limited to specific tasks, AI agents are more proactive and autonomous.
Utilizing large AI models as their digital brain, these agents can process input information, plan and make decisions, recall and reflect, interact and collaborate, leverage various tools, and take decisive action. As a result, AI agents exhibit a higher level of autonomy in addressing medical and clinical challenges,
operating within an open-ended action space that enables them to tackle a wide array of tasks across diverse data modalities.
AI agents have shown great application potential and value. They are recently used in novel nanobody design, chemical synthesis and clinical diagnosis.
However, the development of AI agents in the medical AI field is still in its nascent stages, with numerous challenges and risks remain unsolved such as security and safety of AI agents, and the lack of benchmarks and evaluation methods.
Despite all these challenges and risks, AI agents represent a research opportunity that can drive new biomedical discoveries and transform the landscape of current healthcare systems and clinical practices.
This workshop will serve as a vital platform for researchers, clinicians, and industry leaders to come together and share insights on the transformative power of AI agents. By fostering a collaborative environment, we aim to:
- Showcase Cutting-Edge Research: Attendees will gain access to the latest findings and innovations in AI agents for medicine and healthcare, equipping them with knowledge that can enhance their own work.
- Address Challenges Head-On: Through open discussions, we will explore the potential risks associated with AI implementation in healthcare, including bias in algorithms and the importance of transparency in AI decision-making.
- Promote Collaboration: The workshop will encourage networking and partnerships among participants, paving the way for interdisciplinary collaborations that can drive future research and development in medical AI agents.
- Inspire Policy and Practice: By bringing together key stakeholders, we aim to contribute to the development of best practices and policies that ensure the responsible use of AI agents in medicine and healthcare.
Time Schedule
| 08:00am | 08:05am |
Opening Remarks
Prof. Ehsan Adeli
|
| 08:05am | 08:30am |
Invited Talk: Finding the scaling law of AI agents
Speaker: Dr. Guohao Li (Industrial)
|
| 08:30am | 08:55am |
Invited Talk: Agentic AI in general surgery
Speaker: Dr. Kyle Lam (Clinical)
|
| 08:55am | 09:55am |
Oral Session #1
Session Chair: Dr. Jianing Qiu
|
| 09:55am | 10:20am |
Coffee Break and Poster Session
|
| 10:20am | 10:45am |
Invited Talk
Speaker: Prof. James Zou (Academic)
|
| 10:45am | 11:10am |
Invited Talk
Speaker: Prof. Marinka Zitnik (Academic)
|
| 11:10am | 12:10pm |
Oral Session #2
Session Chair: Dr. Baoru Huang
|
| 12:10pm | 12:25pm |
Award Announcement
Prof. Ehsan Adeli, Prof. Wu Yuan, Prof. Daniel Rueckert
|
| 12:25pm | 12:30pm |
Closing Remarks
Prof. Wu Yuan
|
Speakers
Prof. James Zou (Academic)
Associate Professor of Biomedical Data Science, Stanford University
Prof. Marinka Zitnik (Academic)
Associate Professor of Biomedical Informatics, Harvard Medical School
Dr. Guohao Li (Industrial)
Founder of CAMEL-AI (the start-up company that developed the world's first LLM multi-agent framework)
Dr. Kyle Lam (Clinical)
NIHR Academic Clinical Fellow in General SurgerySubmisstion
Submission portal: MICCAI 2025 Workshop MedAgent (OpenReview)
Manuscript template: Papers must be submitted electronically in searchable PDF format using the provided MICCAI 2025 LaTeX or MS Word templates. Manuscripts can be up to 8 pages (text, figures and tables) plus up to 2 pages of references. No modifications to the templates are permitted.
Anonymization: The MICCAI Workshop review process is double-blinded, i.e. the names of the authors, reviewers, and Area Chairs are not revealed to each other. Authors must therefore ensure that all submitted content is anonymized. Please note that the author section is already anonymized in the newly provided templates. Editing the anonymized author list to save space will be considered a format violation.
Paper submission due: June 25, 2025.
Notification to paper decision: July 16, 2025.
Camera ready papers due: July 30, 2025.
The accepted papers will be presented as either an oral or poster presentation. At least one author of each accepted submission must present the paper at the workshop.
The Best Workshop Paper Award and Best Poster Award will be presented to honor exceptional contributions among the accepted submissions, with a cash prize of 1,000 US dollors for each award.
Call for Papers
We invite submissions including but not limited to the following topics:
New theories, principles, and structures of medical and clinical AI agents.
New reasoning, planning, and decision-making strategies of medical and clinical AI agents.
New evaluation paradigms and benchmarks of medical and clinical AI agents.
Large-scale datasets and tool usage repositories for developing medical and clinical AI agents
Adversarial robustness of medical and clinical AI agents
Applications of AI agents in medicine and healthcare.
Scaling law of medical and clinical AI agents.
Interpretability and explainability of medical and clinical AI agents.
Large-scale agent-based modelling in digital health and medicine.
Multiagent systems in medicine and healthcare.
Decentralized methods for developing and deploying medical and clinical AI agents.
AI agent ethics, safety, privacy, and regulations in medicine and healthcare .
Organizers
Jianing Qiu
The Chinese University of Hong Kong
Baoru Huang
The University of Liverpool
Anh Nguyen
The University of Liverpool
Weidi Xie
Shanghai Jiao Tong University
Ehsan Adeli
Stanford University
Daniel Rueckert
Technical University of Munich & Imperial College London
Wu Yuan
The Chinese University of Hong Kongprogramme commitee
- Lin Li (University of Oxford)
- Jiankai Sun (Stanford University)
- Haibao Yu (The University of Hong Kong)
- Sheng Liu (Stanford University)
- Linyuan Li (The Chinese University of Hong Kong)
- Jiawei Ma (The City University of Hong Kong)
- Emma Anran Ran (The Chinese University of Hong Kong)
- Bang Zheng (Peking University)
- Artur Krzysztof Banach (EPFL)
- Frank P.-W. Lo (Imperial College London)
Sponsors
Contact
Address
Daejeon, Republic of Korea
Email Us
medworkshop2025@outlook.com