@inproceedings{fan-etal-2025-ai,
title = "{AI} Hospital: Benchmarking Large Language Models in a Multi-agent Medical Interaction Simulator",
author = "Fan, Zhihao and
Wei, Lai and
Tang, Jialong and
Chen, Wei and
Siyuan, Wang and
Wei, Zhongyu and
Huang, Fei",
editor = "Rambow, Owen and
Wanner, Leo and
Apidianaki, Marianna and
Al-Khalifa, Hend and
Eugenio, Barbara Di and
Schockaert, Steven",
booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.coling-main.680/",
pages = "10183--10213",
abstract = "Artificial intelligence has significantly revolutionized healthcare, particularly through large language models (LLMs) that demonstrate superior performance in static medical question answering benchmarks. However, evaluating the potential of LLMs for real-world clinical applications remains challenging due to the intricate nature of doctor-patient interactions. To address this, we introduce AI Hospital, a multi-agent framework emulating dynamic medical interactions between Doctor as player and NPCs including Patient and Examiner. This setup allows for more practical assessments of LLMs in simulated clinical scenarios. We develop the Multi-View Medical Evaluation (MVME) benchmark, utilizing high-quality Chinese medical records and multiple evaluation strategies to quantify the performance of LLM-driven Doctor agents on symptom collection, examination recommendations, and diagnoses. Additionally, a dispute resolution collaborative mechanism is proposed to enhance medical interaction capabilities through iterative discussions. Despite improvements, current LLMs (including GPT-4) still exhibit significant performance gaps in multi-turn interactive scenarios compared to non-interactive scenarios. Our findings highlight the need for further research to bridge these gaps and improve LLMs' clinical decision-making capabilities. Our data, code, and experimental results are all open-sourced at https://github.com/LibertFan/AI{\_}Hospital."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fan-etal-2025-ai">
<titleInfo>
<title>AI Hospital: Benchmarking Large Language Models in a Multi-agent Medical Interaction Simulator</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhihao</namePart>
<namePart type="family">Fan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lai</namePart>
<namePart type="family">Wei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jialong</namePart>
<namePart type="family">Tang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wang</namePart>
<namePart type="family">Siyuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhongyu</namePart>
<namePart type="family">Wei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 31st International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marianna</namePart>
<namePart type="family">Apidianaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="given">Di</namePart>
<namePart type="family">Eugenio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Schockaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Artificial intelligence has significantly revolutionized healthcare, particularly through large language models (LLMs) that demonstrate superior performance in static medical question answering benchmarks. However, evaluating the potential of LLMs for real-world clinical applications remains challenging due to the intricate nature of doctor-patient interactions. To address this, we introduce AI Hospital, a multi-agent framework emulating dynamic medical interactions between Doctor as player and NPCs including Patient and Examiner. This setup allows for more practical assessments of LLMs in simulated clinical scenarios. We develop the Multi-View Medical Evaluation (MVME) benchmark, utilizing high-quality Chinese medical records and multiple evaluation strategies to quantify the performance of LLM-driven Doctor agents on symptom collection, examination recommendations, and diagnoses. Additionally, a dispute resolution collaborative mechanism is proposed to enhance medical interaction capabilities through iterative discussions. Despite improvements, current LLMs (including GPT-4) still exhibit significant performance gaps in multi-turn interactive scenarios compared to non-interactive scenarios. Our findings highlight the need for further research to bridge these gaps and improve LLMs’ clinical decision-making capabilities. Our data, code, and experimental results are all open-sourced at https://github.com/LibertFan/AI_Hospital.</abstract>
<identifier type="citekey">fan-etal-2025-ai</identifier>
<location>
<url>https://aclanthology.org/2025.coling-main.680/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>10183</start>
<end>10213</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AI Hospital: Benchmarking Large Language Models in a Multi-agent Medical Interaction Simulator
%A Fan, Zhihao
%A Wei, Lai
%A Tang, Jialong
%A Chen, Wei
%A Siyuan, Wang
%A Wei, Zhongyu
%A Huang, Fei
%Y Rambow, Owen
%Y Wanner, Leo
%Y Apidianaki, Marianna
%Y Al-Khalifa, Hend
%Y Eugenio, Barbara Di
%Y Schockaert, Steven
%S Proceedings of the 31st International Conference on Computational Linguistics
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F fan-etal-2025-ai
%X Artificial intelligence has significantly revolutionized healthcare, particularly through large language models (LLMs) that demonstrate superior performance in static medical question answering benchmarks. However, evaluating the potential of LLMs for real-world clinical applications remains challenging due to the intricate nature of doctor-patient interactions. To address this, we introduce AI Hospital, a multi-agent framework emulating dynamic medical interactions between Doctor as player and NPCs including Patient and Examiner. This setup allows for more practical assessments of LLMs in simulated clinical scenarios. We develop the Multi-View Medical Evaluation (MVME) benchmark, utilizing high-quality Chinese medical records and multiple evaluation strategies to quantify the performance of LLM-driven Doctor agents on symptom collection, examination recommendations, and diagnoses. Additionally, a dispute resolution collaborative mechanism is proposed to enhance medical interaction capabilities through iterative discussions. Despite improvements, current LLMs (including GPT-4) still exhibit significant performance gaps in multi-turn interactive scenarios compared to non-interactive scenarios. Our findings highlight the need for further research to bridge these gaps and improve LLMs’ clinical decision-making capabilities. Our data, code, and experimental results are all open-sourced at https://github.com/LibertFan/AI_Hospital.
%U https://aclanthology.org/2025.coling-main.680/
%P 10183-10213
Markdown (Informal)
[AI Hospital: Benchmarking Large Language Models in a Multi-agent Medical Interaction Simulator](https://aclanthology.org/2025.coling-main.680/) (Fan et al., COLING 2025)
ACL