<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2026-proactis">
    <titleInfo>
        <title>ProActIS: Boosting LLMs’ Proactive Information Seeking in Dynamic Clinical Workflows with a Lightweight Exam Proposer</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ruiyang</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yushi</namePart>
        <namePart type="family">Feng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Liang</namePart>
        <namePart type="family">Peng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Lequan</namePart>
        <namePart type="family">Yu</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>Large language models (LLMs) have shown strong promise as clinical reasoning agents, yet most benchmarks assume complete evidence availability before reasoning begins. However, real clinical practice unfolds through dynamic clinical workflows with progressive disclosure of patient evidence, requiring clinicians to decide what evidence to acquire next from partial and evolving patient states. This mismatch exposes a bottleneck in proactive evidence acquisition for LLM-based clinical agents. To address this gap, we introduce **ProActIS**, a lightweight state-conditioned examination proposer for proactive evidence acquisition. Given an evolving patient state, ProActIS ranks standardized laboratory, microbiology, and radiology examinations, together with STOP, through structured patient-state decomposition and action-card encoding. We construct an MIMIC-IV benchmark with 81,960 hospital admissions and 860,099 turn-level patient-state/examination pairs, using explicit diagnosis/result filtering and retrospective leakage sensitivity analysis over 129 standardized examination actions plus STOP (130 actions). On full-bank next-examination ranking, ProActIS achieves 0.6028 Recall@1, 0.8868 Recall@5, and 0.7258 MRR, substantially outperforming frequency and LLM baselines. In LLM-assisted dynamic workflows, ProActIS substantially improves benchmark-level evidence coverage and documented-trajectory alignment for downstream agents, with downstream diagnostic accuracy approaching the corresponding all-information controls.</abstract>
    <identifier type="citekey">zhang-etal-2026-proactis</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-emnlp.462/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>9693</start>
            <end>9709</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T ProActIS: Boosting LLMs’ Proactive Information Seeking in Dynamic Clinical Workflows with a Lightweight Exam Proposer
%A Zhang, Ruiyang
%A Feng, Yushi
%A Peng, Liang
%A Yu, Lequan
%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 zhang-etal-2026-proactis
%X Large language models (LLMs) have shown strong promise as clinical reasoning agents, yet most benchmarks assume complete evidence availability before reasoning begins. However, real clinical practice unfolds through dynamic clinical workflows with progressive disclosure of patient evidence, requiring clinicians to decide what evidence to acquire next from partial and evolving patient states. This mismatch exposes a bottleneck in proactive evidence acquisition for LLM-based clinical agents. To address this gap, we introduce **ProActIS**, a lightweight state-conditioned examination proposer for proactive evidence acquisition. Given an evolving patient state, ProActIS ranks standardized laboratory, microbiology, and radiology examinations, together with STOP, through structured patient-state decomposition and action-card encoding. We construct an MIMIC-IV benchmark with 81,960 hospital admissions and 860,099 turn-level patient-state/examination pairs, using explicit diagnosis/result filtering and retrospective leakage sensitivity analysis over 129 standardized examination actions plus STOP (130 actions). On full-bank next-examination ranking, ProActIS achieves 0.6028 Recall@1, 0.8868 Recall@5, and 0.7258 MRR, substantially outperforming frequency and LLM baselines. In LLM-assisted dynamic workflows, ProActIS substantially improves benchmark-level evidence coverage and documented-trajectory alignment for downstream agents, with downstream diagnostic accuracy approaching the corresponding all-information controls.
%U https://aclanthology.org/2026.findings-emnlp.462/
%P 9693-9709

Markdown (Informal)

[ProActIS: Boosting LLMs’ Proactive Information Seeking in Dynamic Clinical Workflows with a Lightweight Exam Proposer](https://aclanthology.org/2026.findings-emnlp.462/) (Zhang et al., Findings 2026)

• ProActIS: Boosting LLMs’ Proactive Information Seeking in Dynamic Clinical Workflows with a Lightweight Exam Proposer (Zhang et al., Findings 2026)

ACL

• Ruiyang Zhang, Yushi Feng, Liang Peng, and Lequan Yu. 2026. ProActIS: Boosting LLMs’ Proactive Information Seeking in Dynamic Clinical Workflows with a Lightweight Exam Proposer. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 9693–9709, Budapest, Hungary. Association for Computational Linguistics.