Architecting Clinical Collaboration: Multi-Agent Reasoning Systems for Multimodal Medical VQA

• URL: http://arxiv.org/abs/2507.05520v3
• Date: Tue, 26 Aug 2025 14:02:57 GMT
• Title: Architecting Clinical Collaboration: Multi-Agent Reasoning Systems for Multimodal Medical VQA
• Authors: Karishma Thakrar, Shreyas Basavatia, Akshay Daftardar,
• Abstract summary: Dermatological care via telemedicine often lacks the rich context of in-person visits.<n>This study tested seven vision-language models on medical visual question answering across six configurations.
• Score: 1.2744523252873352
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Dermatological care via telemedicine often lacks the rich context of in-person visits. Clinicians must make diagnoses based on a handful of images and brief descriptions, without the benefit of physical exams, second opinions, or reference materials. While many medical AI systems attempt to bridge these gaps with domain-specific fine-tuning, this work hypothesized that mimicking clinical reasoning processes could offer a more effective path forward. This study tested seven vision-language models on medical visual question answering across six configurations: baseline models, fine-tuned variants, and both augmented with either reasoning layers that combine multiple model perspectives, analogous to peer consultation, or retrieval-augmented generation that incorporates medical literature at inference time, serving a role similar to reference-checking. While fine-tuning degraded performance in four of seven models with an average 30% decrease, baseline models collapsed on test data. Clinical-inspired architectures, meanwhile, achieved up to 70% accuracy, maintaining performance on unseen data while generating explainable, literature-grounded outputs critical for clinical adoption. These findings demonstrate that medical AI succeeds by reconstructing the collaborative and evidence-based practices fundamental to clinical diagnosis.

Related papers

• MedCollab: Causal-Driven Multi-Agent Collaboration for Full-Cycle Clinical Diagnosis via IBIS-Structured Argumentation [6.334763475104128]
  We present MedCollab, a novel multi-agent framework that emulates the hierarchical consultation workflow of modern hospitals.<n>The framework incorporates a dynamic specialist recruitment mechanism that adaptively assembles clinical and examination agents according to patient-specific symptoms and examination results.
  arXiv  Detail & Related papers  (2026-03-01T14:25:58Z)
• AgentsEval: Clinically Faithful Evaluation of Medical Imaging Reports via Multi-Agent Reasoning [73.50200033931148]
  We introduce AgentsEval, a multi-agent stream reasoning framework that emulates the collaborative diagnostic workflow of radiologists.<n>By dividing the evaluation process into interpretable steps including criteria definition, evidence extraction, alignment, and consistency scoring, AgentsEval provides explicit reasoning traces and structured clinical feedback.<n> Experimental results demonstrate that AgentsEval delivers clinically aligned, semantically faithful, and interpretable evaluations that remain robust under paraphrastic, semantic, and stylistic perturbations.
  arXiv  Detail & Related papers  (2026-01-23T11:59:13Z)
• MedDialogRubrics: A Comprehensive Benchmark and Evaluation Framework for Multi-turn Medical Consultations in Large Language Models [15.91764739198419]
  We present MedDialogRubrics, a novel benchmark comprising 5,200 synthetically constructed patient cases and over 60,000 fine-grained evaluation rubrics.<n>Our framework employs a multi-agent system to synthesize realistic patient records and chief complaints without accessing real-world electronic health records.
  arXiv  Detail & Related papers  (2026-01-06T13:56:33Z)
• The Illusion of Clinical Reasoning: A Benchmark Reveals the Pervasive Gap in Vision-Language Models for Clinical Competency [38.68458713626548]
  Current benchmarks fail to capture the integrated, multimodal reasoning essential for real-world patient care.<n>This benchmark assesses models across 7 tasks that mirror the clinical reasoning pathway.<n>Current artificial intelligence models are not yet clinically competent for complex, multimodal reasoning.
  arXiv  Detail & Related papers  (2025-12-25T03:33:22Z)
• MedXplain-VQA: Multi-Component Explainable Medical Visual Question Answering [1.4413073343064953]
  We present MedXplain-VQA, a comprehensive framework integrating five explainable AI components to deliver interpretable medical image analysis.<n>The framework leverages a fine-tuned BLIP-2 backbone, medical query reformulation, enhanced Grad-CAM attention, precise region extraction, and structured chain-of-thought reasoning via multi-modal language models.
  arXiv  Detail & Related papers  (2025-10-26T19:23:20Z)
• Simulating Viva Voce Examinations to Evaluate Clinical Reasoning in Large Language Models [51.91760712805404]
  We introduce VivaBench, a benchmark for evaluating sequential clinical reasoning in large language models (LLMs)<n>Our dataset consists of 1762 physician-curated clinical vignettes structured as interactive scenarios that simulate a (oral) examination in medical training.<n>Our analysis identified several failure modes that mirror common cognitive errors in clinical practice.
  arXiv  Detail & Related papers  (2025-10-11T16:24:35Z)
• Medical Reasoning in the Era of LLMs: A Systematic Review of Enhancement Techniques and Applications [59.721265428780946]
  Large Language Models (LLMs) in medicine have enabled impressive capabilities, yet a critical gap remains in their ability to perform systematic, transparent, and verifiable reasoning.<n>This paper provides the first systematic review of this emerging field.<n>We propose a taxonomy of reasoning enhancement techniques, categorized into training-time strategies and test-time mechanisms.
  arXiv  Detail & Related papers  (2025-08-01T14:41:31Z)
• Barriers in Integrating Medical Visual Question Answering into Radiology Workflows: A Scoping Review and Clinicians' Insights [6.5907034989882725]
  Medical Visual Question Answering (MedVQA) is a promising tool to assist radiologists by automating medical image interpretation through question answering.<n>Despite advances in models and datasets, MedVQA's integration into clinical systems remains limited.<n>This study systematically reviews 68 publications and surveys 50 clinicians from India and Thailand to examine MedVQA's practical utility, challenges, and gaps.
  arXiv  Detail & Related papers  (2025-07-09T09:51:20Z)
• MedSeg-R: Reasoning Segmentation in Medical Images with Multimodal Large Language Models [48.24824129683951]
  We introduce medical image reasoning segmentation, a novel task that aims to generate segmentation masks based on complex and implicit medical instructions.<n>To address this, we propose MedSeg-R, an end-to-end framework that leverages the reasoning abilities of MLLMs to interpret clinical questions.<n>It is built on two core components: 1) a global context understanding module that interprets images and comprehends complex medical instructions to generate multi-modal intermediate tokens, and 2) a pixel-level grounding module that decodes these tokens to produce precise segmentation masks.
  arXiv  Detail & Related papers  (2025-06-12T08:13:38Z)
• Lingshu: A Generalist Foundation Model for Unified Multimodal Medical Understanding and Reasoning [57.873833577058]
  We build a multimodal dataset enriched with extensive medical knowledge.<n>We then introduce our medical-specialized MLLM: Lingshu.<n>Lingshu undergoes multi-stage training to embed medical expertise and enhance its task-solving capabilities.
  arXiv  Detail & Related papers  (2025-06-08T08:47:30Z)
• Hierarchical Modeling for Medical Visual Question Answering with Cross-Attention Fusion [4.821565717653691]
  Medical Visual Question Answering (Med-VQA) answers clinical questions using medical images, aiding diagnosis.<n>This study proposes a HiCA-VQA method, including two modules: Hierarchical Prompting for fine-grained medical questions and Hierarchical Answer Decoders.<n> Experiments on the Rad-Restruct benchmark demonstrate that the HiCA-VQA framework better outperforms existing state-of-the-art methods in answering hierarchical fine-grained questions.
  arXiv  Detail & Related papers  (2025-04-04T03:03:12Z)
• MedAgentsBench: Benchmarking Thinking Models and Agent Frameworks for Complex Medical Reasoning [34.93995619867384]
  Large Language Models (LLMs) have shown impressive performance on existing medical question-answering benchmarks.<n>We present MedAgentsBench, a benchmark that focuses on challenging medical questions requiring multi-step clinical reasoning, diagnosis formulation, and treatment planning-scenarios.
  arXiv  Detail & Related papers  (2025-03-10T15:38:44Z)
• Structured Outputs Enable General-Purpose LLMs to be Medical Experts [50.02627258858336]
  Large language models (LLMs) often struggle with open-ended medical questions.<n>We propose a novel approach utilizing structured medical reasoning.<n>Our approach achieves the highest Factuality Score of 85.8, surpassing fine-tuned models.
  arXiv  Detail & Related papers  (2025-03-05T05:24:55Z)
• MedCoT: Medical Chain of Thought via Hierarchical Expert [48.91966620985221]
  This paper presents MedCoT, a novel hierarchical expert verification reasoning chain method.<n>It is designed to enhance interpretability and accuracy in biomedical imaging inquiries.<n> Experimental evaluations on four standard Med-VQA datasets demonstrate that MedCoT surpasses existing state-of-the-art approaches.
  arXiv  Detail & Related papers  (2024-12-18T11:14:02Z)
• Medchain: Bridging the Gap Between LLM Agents and Clinical Practice through Interactive Sequential Benchmarking [58.25862290294702]
  We present MedChain, a dataset of 12,163 clinical cases that covers five key stages of clinical workflow.<n>We also propose MedChain-Agent, an AI system that integrates a feedback mechanism and a MCase-RAG module to learn from previous cases and adapt its responses.
  arXiv  Detail & Related papers  (2024-12-02T15:25:02Z)
• GEMeX: A Large-Scale, Groundable, and Explainable Medical VQA Benchmark for Chest X-ray Diagnosis [44.76975131560712]
  We introduce a large-scale, Groundable, and Explainable Medical VQA benchmark for chest X-ray diagnosis (GEMeX)<n>With 151,025 images and 1,605,575 questions, GEMeX is the currently largest chest X-ray VQA dataset.
  arXiv  Detail & Related papers  (2024-11-25T07:36:46Z)
• WangLab at MEDIQA-M3G 2024: Multimodal Medical Answer Generation using Large Language Models [5.7931394318054155]
  We report results for two standalone solutions under the English category of the task. We identify the multi-stage LLM approach and the CLIP image classification approach as promising avenues for further investigation.
  arXiv  Detail & Related papers  (2024-04-22T20:29:58Z)
• MedThink: Explaining Medical Visual Question Answering via Multimodal Decision-Making Rationale [19.94415334436024]
  We devise a semi-automated annotation process to streamline data preparation and build new benchmark MedVQA datasets. These datasets provide intermediate medical decision-making rationales generated by multimodal large language models and human annotations. We also design a novel framework, MedThink, which finetunes lightweight pretrained generative models by incorporating medical decision-making rationales.
  arXiv  Detail & Related papers  (2024-04-18T17:53:19Z)
• Benchmarking Large Language Models on Answering and Explaining Challenging Medical Questions [19.436999992810797]
  We construct two new datasets: JAMA Clinical Challenge and Medbullets.<n> JAMA Clinical Challenge consists of questions based on challenging clinical cases, while Medbullets comprises simulated clinical questions.<n>We evaluate seven LLMs on the two datasets using various prompts.
  arXiv  Detail & Related papers  (2024-02-28T05:44:41Z)
• A Transformer-based representation-learning model with unified processing of multimodal input for clinical diagnostics [63.106382317917344]
  We report a Transformer-based representation-learning model as a clinical diagnostic aid that processes multimodal input in a unified manner. The unified model outperformed an image-only model and non-unified multimodal diagnosis models in the identification of pulmonary diseases.
  arXiv  Detail & Related papers  (2023-06-01T16:23:47Z)
• This Patient Looks Like That Patient: Prototypical Networks for Interpretable Diagnosis Prediction from Clinical Text [56.32427751440426]
  In clinical practice such models must not only be accurate, but provide doctors with interpretable and helpful results. We introduce ProtoPatient, a novel method based on prototypical networks and label-wise attention. We evaluate the model on two publicly available clinical datasets and show that it outperforms existing baselines.
  arXiv  Detail & Related papers  (2022-10-16T10:12:07Z)
• Q-Net: Query-Informed Few-Shot Medical Image Segmentation [5.615188751640673]
  We propose a Query-informed Meta-FSS approach, which mimics the learning mechanism of an expert clinician. We build Q-Net based on ADNet, a recently proposed anomaly detection-inspired method. Q-Net achieves state-of-the-art performance on two widely used datasets.
  arXiv  Detail & Related papers  (2022-08-24T11:36:53Z)
• Inheritance-guided Hierarchical Assignment for Clinical Automatic Diagnosis [50.15205065710629]
  Clinical diagnosis, which aims to assign diagnosis codes for a patient based on the clinical note, plays an essential role in clinical decision-making. We propose a novel framework to combine the inheritance-guided hierarchical assignment and co-occurrence graph propagation for clinical automatic diagnosis.
  arXiv  Detail & Related papers  (2021-01-27T13:16:51Z)
• MedDG: An Entity-Centric Medical Consultation Dataset for Entity-Aware Medical Dialogue Generation [86.38736781043109]
  We build and release a large-scale high-quality Medical Dialogue dataset related to 12 types of common Gastrointestinal diseases named MedDG. We propose two kinds of medical dialogue tasks based on MedDG dataset. One is the next entity prediction and the other is the doctor response generation. Experimental results show that the pre-train language models and other baselines struggle on both tasks with poor performance in our dataset.
  arXiv  Detail & Related papers  (2020-10-15T03:34:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.