<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yuan-etal-2026-mixed">
    <titleInfo>
        <title>Do Mixed-Vendor Multi-Agent LLMs Improve Clinical Diagnosis?</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Grace</namePart>
        <namePart type="given">Chang</namePart>
        <namePart type="family">Yuan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xiaoman</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sung</namePart>
        <namePart type="given">Eun</namePart>
        <namePart type="family">Kim</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Pranav</namePart>
        <namePart type="family">Rajpurkar</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-03</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 1st Workshop on Linguistic Analysis for Health (HeaLing 2026)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Vera</namePart>
            <namePart type="family">Danilova</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Murathan</namePart>
            <namePart type="family">Kurfalı</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ylva</namePart>
            <namePart type="family">Söderfeldt</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Julia</namePart>
            <namePart type="family">Reed</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Andrew</namePart>
            <namePart type="family">Burchell</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Rabat, Morocco</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-367-8</identifier>
    </relatedItem>
    <abstract>Multi-agent large language model (LLM) systems have emerged as a promising approach for clinical diagnosis, leveraging collaboration among agents to refine medical reasoning. However, most existing frameworks rely on single-vendor teams (e.g., multiple agents from the same model family), which risk correlated failure modes that reinforce shared biases rather than correcting them. We investigate the impact of vendor diversity by comparing Single-LLM, Single-Vendor, and Mixed-Vendor Multi-Agent Conversation (MAC) frameworks. Using three doctor agents instantiated with o4-mini, Gemini-2.5-Pro, and Claude-4.5-Sonnet, we evaluate performance on RareBench and DiagnosisArena. Mixed-vendor configurations consistently outperform single-vendor counterparts, achieving state-of-the-art recall and accuracy. Overlap analysis reveals the underlying mechanism: mixed-vendor teams pool complementary inductive biases, surfacing correct diagnoses that individual models or homogeneous teams collectively miss. These results highlight vendor diversity as a key design principle for robust clinical diagnostic systems.</abstract>
    <identifier type="citekey">yuan-etal-2026-mixed</identifier>
    <location>
        <url>https://aclanthology.org/2026.healing-1.1/</url>
    </location>
    <part>
        <date>2026-03</date>
        <extent unit="page">
            <start>1</start>
            <end>18</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Do Mixed-Vendor Multi-Agent LLMs Improve Clinical Diagnosis?
%A Yuan, Grace Chang
%A Zhang, Xiaoman
%A Kim, Sung Eun
%A Rajpurkar, Pranav
%Y Danilova, Vera
%Y Kurfalı, Murathan
%Y Söderfeldt, Ylva
%Y Reed, Julia
%Y Burchell, Andrew
%S Proceedings of the 1st Workshop on Linguistic Analysis for Health (HeaLing 2026)
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-367-8
%F yuan-etal-2026-mixed
%X Multi-agent large language model (LLM) systems have emerged as a promising approach for clinical diagnosis, leveraging collaboration among agents to refine medical reasoning. However, most existing frameworks rely on single-vendor teams (e.g., multiple agents from the same model family), which risk correlated failure modes that reinforce shared biases rather than correcting them. We investigate the impact of vendor diversity by comparing Single-LLM, Single-Vendor, and Mixed-Vendor Multi-Agent Conversation (MAC) frameworks. Using three doctor agents instantiated with o4-mini, Gemini-2.5-Pro, and Claude-4.5-Sonnet, we evaluate performance on RareBench and DiagnosisArena. Mixed-vendor configurations consistently outperform single-vendor counterparts, achieving state-of-the-art recall and accuracy. Overlap analysis reveals the underlying mechanism: mixed-vendor teams pool complementary inductive biases, surfacing correct diagnoses that individual models or homogeneous teams collectively miss. These results highlight vendor diversity as a key design principle for robust clinical diagnostic systems.
%U https://aclanthology.org/2026.healing-1.1/
%P 1-18

Markdown (Informal)

[Do Mixed-Vendor Multi-Agent LLMs Improve Clinical Diagnosis?](https://aclanthology.org/2026.healing-1.1/) (Yuan et al., HeaLing 2026)

• Do Mixed-Vendor Multi-Agent LLMs Improve Clinical Diagnosis? (Yuan et al., HeaLing 2026)

ACL

• Grace Chang Yuan, Xiaoman Zhang, Sung Eun Kim, and Pranav Rajpurkar. 2026. Do Mixed-Vendor Multi-Agent LLMs Improve Clinical Diagnosis?. In Proceedings of the 1st Workshop on Linguistic Analysis for Health (HeaLing 2026), pages 1–18, Rabat, Morocco. Association for Computational Linguistics.