<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhu-etal-2026-medinsightbench">
    <titleInfo>
        <title>MedInsightBench: Evaluating Medical Analytics Agents Through Multi-Step Insight Discovery in Multi-modal Medical Data</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Zhenghao</namePart>
        <namePart type="family">Zhu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Chuxue</namePart>
        <namePart type="family">Cao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yuanfeng</namePart>
        <namePart type="family">Song</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xing</namePart>
        <namePart type="family">Chen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Caleb</namePart>
        <namePart type="given">Chen</namePart>
        <namePart type="family">Cao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sirui</namePart>
        <namePart type="family">Han</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yike</namePart>
        <namePart type="family">Guo</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>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</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">979-8-89176-459-0</identifier>
    </relatedItem>
    <abstract>In medical data analysis, extracting deep insights from complex multi-modal pathological data is essential for enhancing patient care, diagnostic accuracy, and healthcare operations. Despite this clinical significance, current benchmarks fail to adequately evaluate Large Multi-modal Models (LMMs) on medical insight discovery. Therefore, we introduce MedInsightBench, the first benchmark comprising 332 curated cases from The Cancer Genome Atlas, each annotated with expert-derived insights. Instead of simple QA, this benchmark evaluates whether LMMs can derive clinically grounded insights tied to tumor staging, prognosis, and biomarker expression. Our initial analysis reveals that existing LMMs struggle with MedInsightBench, primarily due to a lack of domain expertise and an inability to perform multi-step reasoning. Consequently, we propose MedInsightAgent, an automated agent framework featuring three specialized modules: Visual Root Finder, Analytical Insight Agent, and Follow-up Question Composer. Extensive experiments confirm that MedInsightAgent effectively addresses the limitations of existing models, consistently demonstrating superior performance in discovering complex medical insights.</abstract>
    <identifier type="citekey">zhu-etal-2026-medinsightbench</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.1272/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>28984</start>
            <end>29016</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T MedInsightBench: Evaluating Medical Analytics Agents Through Multi-Step Insight Discovery in Multi-modal Medical Data
%A Zhu, Zhenghao
%A Cao, Chuxue
%A Song, Yuanfeng
%A Chen, Xing
%A Cao, Caleb Chen
%A Han, Sirui
%A Guo, Yike
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F zhu-etal-2026-medinsightbench
%X In medical data analysis, extracting deep insights from complex multi-modal pathological data is essential for enhancing patient care, diagnostic accuracy, and healthcare operations. Despite this clinical significance, current benchmarks fail to adequately evaluate Large Multi-modal Models (LMMs) on medical insight discovery. Therefore, we introduce MedInsightBench, the first benchmark comprising 332 curated cases from The Cancer Genome Atlas, each annotated with expert-derived insights. Instead of simple QA, this benchmark evaluates whether LMMs can derive clinically grounded insights tied to tumor staging, prognosis, and biomarker expression. Our initial analysis reveals that existing LMMs struggle with MedInsightBench, primarily due to a lack of domain expertise and an inability to perform multi-step reasoning. Consequently, we propose MedInsightAgent, an automated agent framework featuring three specialized modules: Visual Root Finder, Analytical Insight Agent, and Follow-up Question Composer. Extensive experiments confirm that MedInsightAgent effectively addresses the limitations of existing models, consistently demonstrating superior performance in discovering complex medical insights.
%U https://aclanthology.org/2026.emnlp-main.1272/
%P 28984-29016

Markdown (Informal)

[MedInsightBench: Evaluating Medical Analytics Agents Through Multi-Step Insight Discovery in Multi-modal Medical Data](https://aclanthology.org/2026.emnlp-main.1272/) (Zhu et al., EMNLP 2026)

• MedInsightBench: Evaluating Medical Analytics Agents Through Multi-Step Insight Discovery in Multi-modal Medical Data (Zhu et al., EMNLP 2026)

ACL

• Zhenghao Zhu, Chuxue Cao, Yuanfeng Song, Xing Chen, Caleb Chen Cao, Sirui Han, and Yike Guo. 2026. MedInsightBench: Evaluating Medical Analytics Agents Through Multi-Step Insight Discovery in Multi-modal Medical Data. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 28984–29016, Budapest, Hungary. Association for Computational Linguistics.