@inproceedings{fan-etal-2026-medace,
title = "{M}ed{ACE}: A Time-Aware Asynchronous Clinical Environment for Long-Horizon Medical Treatment Decision-Making",
author = "Fan, Zhiting and
Chen, Ruizhe and
Wang, Hualiang and
Peng, Ru and
Meng, Zijie and
MA, Wen and
Wu, Jian and
Liu, Zuozhu",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.2316/",
pages = "49730--49743",
ISBN = "979-8-89176-462-0",
abstract = "Recent advances in Medical Large Language Models have shown strong performance in medical question answering and clinical knowledge understanding, yet real-world clinical practice requires long-horizon, dynamic treatment decision-making rather than static prediction. Existing medical agent environments are mostly turn-based, assuming patient states change after actions while overlooking natural disease progression and delayed treatment effects. We propose MedACE, a time-aware asynchronous clinical world model, where patient evolution is formulated as an elapsed-time-conditioned process driven by historical observations, treatment actions, clinical context, and disease-level knowledge. Built from timestamped MIMIC-IV trajectories, our JEPA-style simulator, MedWorld-JEPA, learns future patient state representations in latent space rather than directly generating noisy clinical observations. Based on this simulator, we construct an asynchronous treatment environment with global time advancement, closed-loop patient simulation, multi-step physician-agent interaction, and outcome-grounded rewards. Experiments on Hospital and ICU scenarios demonstrate competitive physiological forecasting, strong clinical consistency, and the importance of jointly modeling time, disease progression, and treatment effects. Agent evaluations further show that current LLM-based physicians struggle with long-horizon treatment decisions, highlighting our environment as a challenging foundation for future medical treatment agents."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fan-etal-2026-medace">
<titleInfo>
<title>MedACE: A Time-Aware Asynchronous Clinical Environment for Long-Horizon Medical Treatment Decision-Making</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhiting</namePart>
<namePart type="family">Fan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruizhe</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hualiang</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ru</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zijie</namePart>
<namePart type="family">Meng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wen</namePart>
<namePart type="family">MA</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jian</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zuozhu</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Recent advances in Medical Large Language Models have shown strong performance in medical question answering and clinical knowledge understanding, yet real-world clinical practice requires long-horizon, dynamic treatment decision-making rather than static prediction. Existing medical agent environments are mostly turn-based, assuming patient states change after actions while overlooking natural disease progression and delayed treatment effects. We propose MedACE, a time-aware asynchronous clinical world model, where patient evolution is formulated as an elapsed-time-conditioned process driven by historical observations, treatment actions, clinical context, and disease-level knowledge. Built from timestamped MIMIC-IV trajectories, our JEPA-style simulator, MedWorld-JEPA, learns future patient state representations in latent space rather than directly generating noisy clinical observations. Based on this simulator, we construct an asynchronous treatment environment with global time advancement, closed-loop patient simulation, multi-step physician-agent interaction, and outcome-grounded rewards. Experiments on Hospital and ICU scenarios demonstrate competitive physiological forecasting, strong clinical consistency, and the importance of jointly modeling time, disease progression, and treatment effects. Agent evaluations further show that current LLM-based physicians struggle with long-horizon treatment decisions, highlighting our environment as a challenging foundation for future medical treatment agents.</abstract>
<identifier type="citekey">fan-etal-2026-medace</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.2316/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>49730</start>
<end>49743</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MedACE: A Time-Aware Asynchronous Clinical Environment for Long-Horizon Medical Treatment Decision-Making
%A Fan, Zhiting
%A Chen, Ruizhe
%A Wang, Hualiang
%A Peng, Ru
%A Meng, Zijie
%A MA, Wen
%A Wu, Jian
%A Liu, Zuozhu
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F fan-etal-2026-medace
%X Recent advances in Medical Large Language Models have shown strong performance in medical question answering and clinical knowledge understanding, yet real-world clinical practice requires long-horizon, dynamic treatment decision-making rather than static prediction. Existing medical agent environments are mostly turn-based, assuming patient states change after actions while overlooking natural disease progression and delayed treatment effects. We propose MedACE, a time-aware asynchronous clinical world model, where patient evolution is formulated as an elapsed-time-conditioned process driven by historical observations, treatment actions, clinical context, and disease-level knowledge. Built from timestamped MIMIC-IV trajectories, our JEPA-style simulator, MedWorld-JEPA, learns future patient state representations in latent space rather than directly generating noisy clinical observations. Based on this simulator, we construct an asynchronous treatment environment with global time advancement, closed-loop patient simulation, multi-step physician-agent interaction, and outcome-grounded rewards. Experiments on Hospital and ICU scenarios demonstrate competitive physiological forecasting, strong clinical consistency, and the importance of jointly modeling time, disease progression, and treatment effects. Agent evaluations further show that current LLM-based physicians struggle with long-horizon treatment decisions, highlighting our environment as a challenging foundation for future medical treatment agents.
%U https://aclanthology.org/2026.findings-emnlp.2316/
%P 49730-49743
Markdown (Informal)
[MedACE: A Time-Aware Asynchronous Clinical Environment for Long-Horizon Medical Treatment Decision-Making](https://aclanthology.org/2026.findings-emnlp.2316/) (Fan et al., Findings 2026)
ACL
- Zhiting Fan, Ruizhe Chen, Hualiang Wang, Ru Peng, Zijie Meng, Wen MA, Jian Wu, and Zuozhu Liu. 2026. MedACE: A Time-Aware Asynchronous Clinical Environment for Long-Horizon Medical Treatment Decision-Making. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 49730–49743, Budapest, Hungary. Association for Computational Linguistics.