Agent Hospital: A Simulacrum of Hospital with Evolvable Medical Agents
Junkai Li, Yunghwei Lai, Weitao Li, Jingyi Ren, Meng Zhang, Xinhui, Kang, Siyu Wang, Peng Li, Ya-Qin Zhang, Weizhi Ma, and Yang Liu

TL;DR
This paper presents Agent Hospital, a simulated environment where autonomous LLM-powered medical agents evolve through treatment interactions, outperforming existing methods on medical exam benchmarks and offering broad application potential.
Contribution
Introduction of a hospital simulacrum with evolving LLM-based medical agents that improve through treatment interactions without manual data labeling.
Findings
Evolved doctor agents outperform state-of-the-art on MedQA benchmark.
Simulacrum enables large-scale agent evolution in a simulated medical environment.
Potential applications extend beyond medical AI.
Abstract
The recent rapid development of large language models (LLMs) has sparked a new wave of technological revolution in medical artificial intelligence (AI). While LLMs are designed to understand and generate text like a human, autonomous agents that utilize LLMs as their "brain" have exhibited capabilities beyond text processing such as planning, reflection, and using tools by enabling their "bodies" to interact with the environment. We introduce a simulacrum of hospital called Agent Hospital that simulates the entire process of treating illness, in which all patients, nurses, and doctors are LLM-powered autonomous agents. Within the simulacrum, doctor agents are able to evolve by treating a large number of patient agents without the need to label training data manually. After treating tens of thousands of patient agents in the simulacrum (human doctors may take several years in the real…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
OpenAI’s ChatGPT: This is Science Fiction!· youtube
Taxonomy
TopicsMulti-Agent Systems and Negotiation · Modular Robots and Swarm Intelligence · Transportation and Mobility Innovations
