@inproceedings{bose-etal-2026-v,
title = "{V}-{RAM}: A Visual Retrieval-Augmented Multi-Agent Reasoning Framework for Medical Dialogue Diagnosis",
author = "Bose, Shukraditya and
Sinha, Soumen and
Bhat, Ananya R and
Roy, Rahul",
editor = "Kamalloo, Ehsan and
Gontier, Nicolas and
Rozanov, Nikolai and
Hashemzadeh, Maryam and
Arora, Akhil",
booktitle = "Proceedings of the Second Workshop for {RE}search on Agent Language Models ({REALM} 2026)",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.realm-1.41/",
pages = "599--617",
ISBN = "979-8-89176-485-9",
abstract = "Large Vision-Language Models (LVLMs) are increasingly explored for multimodal medical diagnosis, their ability to conduct accurate consultation remains challenging because of unstable visual reasoning and limited tracking of patient information across dialogue turns. To address this problem we present V-RAM (Visual Retrieval-Augmented Multi-Agent Reasoning Framework), a training-free framework for improving LVLM-based multimodal medical dialogue diagnosis. V-RAM improves medical dialogue diagnosis by adding visual retrieval, structured memory, and multi-agent reasoning around a pretrained LVLM. It retrieves similar medical images as diagnostic cues and tracks patient evidence across dialogue turns. The framework operates at inference time, it requires no supervised fine-tuning and can be used with different LVLM backbones. Experiments on benchmark show that V-RAM outperforms existing baselines and the current LVLMs by 7.3{\%} on an average with 86{\%} lesser number of turns that are used for medical dialogue diagnosis."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bose-etal-2026-v">
<titleInfo>
<title>V-RAM: A Visual Retrieval-Augmented Multi-Agent Reasoning Framework for Medical Dialogue Diagnosis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shukraditya</namePart>
<namePart type="family">Bose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Soumen</namePart>
<namePart type="family">Sinha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ananya</namePart>
<namePart type="given">R</namePart>
<namePart type="family">Bhat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rahul</namePart>
<namePart type="family">Roy</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 Second Workshop for REsearch on Agent Language Models (REALM 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ehsan</namePart>
<namePart type="family">Kamalloo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nicolas</namePart>
<namePart type="family">Gontier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikolai</namePart>
<namePart type="family">Rozanov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maryam</namePart>
<namePart type="family">Hashemzadeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Akhil</namePart>
<namePart type="family">Arora</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">979-8-89176-485-9</identifier>
</relatedItem>
<abstract>Large Vision-Language Models (LVLMs) are increasingly explored for multimodal medical diagnosis, their ability to conduct accurate consultation remains challenging because of unstable visual reasoning and limited tracking of patient information across dialogue turns. To address this problem we present V-RAM (Visual Retrieval-Augmented Multi-Agent Reasoning Framework), a training-free framework for improving LVLM-based multimodal medical dialogue diagnosis. V-RAM improves medical dialogue diagnosis by adding visual retrieval, structured memory, and multi-agent reasoning around a pretrained LVLM. It retrieves similar medical images as diagnostic cues and tracks patient evidence across dialogue turns. The framework operates at inference time, it requires no supervised fine-tuning and can be used with different LVLM backbones. Experiments on benchmark show that V-RAM outperforms existing baselines and the current LVLMs by 7.3% on an average with 86% lesser number of turns that are used for medical dialogue diagnosis.</abstract>
<identifier type="citekey">bose-etal-2026-v</identifier>
<location>
<url>https://aclanthology.org/2026.realm-1.41/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>599</start>
<end>617</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T V-RAM: A Visual Retrieval-Augmented Multi-Agent Reasoning Framework for Medical Dialogue Diagnosis
%A Bose, Shukraditya
%A Sinha, Soumen
%A Bhat, Ananya R.
%A Roy, Rahul
%Y Kamalloo, Ehsan
%Y Gontier, Nicolas
%Y Rozanov, Nikolai
%Y Hashemzadeh, Maryam
%Y Arora, Akhil
%S Proceedings of the Second Workshop for REsearch on Agent Language Models (REALM 2026)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-485-9
%F bose-etal-2026-v
%X Large Vision-Language Models (LVLMs) are increasingly explored for multimodal medical diagnosis, their ability to conduct accurate consultation remains challenging because of unstable visual reasoning and limited tracking of patient information across dialogue turns. To address this problem we present V-RAM (Visual Retrieval-Augmented Multi-Agent Reasoning Framework), a training-free framework for improving LVLM-based multimodal medical dialogue diagnosis. V-RAM improves medical dialogue diagnosis by adding visual retrieval, structured memory, and multi-agent reasoning around a pretrained LVLM. It retrieves similar medical images as diagnostic cues and tracks patient evidence across dialogue turns. The framework operates at inference time, it requires no supervised fine-tuning and can be used with different LVLM backbones. Experiments on benchmark show that V-RAM outperforms existing baselines and the current LVLMs by 7.3% on an average with 86% lesser number of turns that are used for medical dialogue diagnosis.
%U https://aclanthology.org/2026.realm-1.41/
%P 599-617
Markdown (Informal)
[V-RAM: A Visual Retrieval-Augmented Multi-Agent Reasoning Framework for Medical Dialogue Diagnosis](https://aclanthology.org/2026.realm-1.41/) (Bose et al., REALM 2026)
ACL