@inproceedings{sviridov-etal-2025-3mdbench,
title = "3{MDB}ench: Medical Multimodal Multi-agent Dialogue Benchmark",
author = "Sviridov, Ivan and
Miftakhova, Amina and
Vladimirovich, Tereshchenko Artemiy and
Zubkova, Galina and
Blinov, Pavel and
Savchenko, Andrey",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-main.1353/",
pages = "26625--26665",
ISBN = "979-8-89176-332-6",
abstract = "Though Large Vision-Language Models (LVLMs) are being actively explored in medicine, their ability to conduct complex real-world telemedicine consultations combining accurate diagnosis with professional dialogue remains underexplored. This paper presents **3MDBench** (**M**edical **M**ultimodal **M**ulti-agent **D**ialogue **Bench**mark), an open-source framework for simulating and evaluating LVLM-driven telemedical consultations. 3MDBench simulates patient variability through temperament-based Patient Agent and evaluates diagnostic accuracy and dialogue quality via Assessor Agent. It includes 2996 cases across 34 diagnoses from real-world telemedicine interactions, combining textual and image-based data. The experimental study compares diagnostic strategies for widely used open and closed-source LVLMs. We demonstrate that multimodal dialogue with internal reasoning improves F1 score by 6.5{\%} over non-dialogue settings, highlighting the importance of context-aware, information-seeking questioning. Moreover, injecting predictions from a diagnostic convolutional neural network into the LVLM{'}s context boosts F1 by up to 20{\%}. Source code is available at https://github.com/univanxx/3mdbench."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sviridov-etal-2025-3mdbench">
<titleInfo>
<title>3MDBench: Medical Multimodal Multi-agent Dialogue Benchmark</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="family">Sviridov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amina</namePart>
<namePart type="family">Miftakhova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tereshchenko</namePart>
<namePart type="given">Artemiy</namePart>
<namePart type="family">Vladimirovich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Galina</namePart>
<namePart type="family">Zubkova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pavel</namePart>
<namePart type="family">Blinov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrey</namePart>
<namePart type="family">Savchenko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-332-6</identifier>
</relatedItem>
<abstract>Though Large Vision-Language Models (LVLMs) are being actively explored in medicine, their ability to conduct complex real-world telemedicine consultations combining accurate diagnosis with professional dialogue remains underexplored. This paper presents **3MDBench** (**M**edical **M**ultimodal **M**ulti-agent **D**ialogue **Bench**mark), an open-source framework for simulating and evaluating LVLM-driven telemedical consultations. 3MDBench simulates patient variability through temperament-based Patient Agent and evaluates diagnostic accuracy and dialogue quality via Assessor Agent. It includes 2996 cases across 34 diagnoses from real-world telemedicine interactions, combining textual and image-based data. The experimental study compares diagnostic strategies for widely used open and closed-source LVLMs. We demonstrate that multimodal dialogue with internal reasoning improves F1 score by 6.5% over non-dialogue settings, highlighting the importance of context-aware, information-seeking questioning. Moreover, injecting predictions from a diagnostic convolutional neural network into the LVLM’s context boosts F1 by up to 20%. Source code is available at https://github.com/univanxx/3mdbench.</abstract>
<identifier type="citekey">sviridov-etal-2025-3mdbench</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-main.1353/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>26625</start>
<end>26665</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T 3MDBench: Medical Multimodal Multi-agent Dialogue Benchmark
%A Sviridov, Ivan
%A Miftakhova, Amina
%A Vladimirovich, Tereshchenko Artemiy
%A Zubkova, Galina
%A Blinov, Pavel
%A Savchenko, Andrey
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-332-6
%F sviridov-etal-2025-3mdbench
%X Though Large Vision-Language Models (LVLMs) are being actively explored in medicine, their ability to conduct complex real-world telemedicine consultations combining accurate diagnosis with professional dialogue remains underexplored. This paper presents **3MDBench** (**M**edical **M**ultimodal **M**ulti-agent **D**ialogue **Bench**mark), an open-source framework for simulating and evaluating LVLM-driven telemedical consultations. 3MDBench simulates patient variability through temperament-based Patient Agent and evaluates diagnostic accuracy and dialogue quality via Assessor Agent. It includes 2996 cases across 34 diagnoses from real-world telemedicine interactions, combining textual and image-based data. The experimental study compares diagnostic strategies for widely used open and closed-source LVLMs. We demonstrate that multimodal dialogue with internal reasoning improves F1 score by 6.5% over non-dialogue settings, highlighting the importance of context-aware, information-seeking questioning. Moreover, injecting predictions from a diagnostic convolutional neural network into the LVLM’s context boosts F1 by up to 20%. Source code is available at https://github.com/univanxx/3mdbench.
%U https://aclanthology.org/2025.emnlp-main.1353/
%P 26625-26665
Markdown (Informal)
[3MDBench: Medical Multimodal Multi-agent Dialogue Benchmark](https://aclanthology.org/2025.emnlp-main.1353/) (Sviridov et al., EMNLP 2025)
ACL
- Ivan Sviridov, Amina Miftakhova, Tereshchenko Artemiy Vladimirovich, Galina Zubkova, Pavel Blinov, and Andrey Savchenko. 2025. 3MDBench: Medical Multimodal Multi-agent Dialogue Benchmark. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 26625–26665, Suzhou, China. Association for Computational Linguistics.