Do Mixed-Vendor Multi-Agent LLMs Improve Clinical Diagnosis?

• URL: http://arxiv.org/abs/2603.04421v1
• Date: Sat, 14 Feb 2026 18:42:58 GMT
• Title: Do Mixed-Vendor Multi-Agent LLMs Improve Clinical Diagnosis?
• Abstract summary: Multi-agent large language model (LLM) systems have emerged as a promising approach for clinical diagnosis.<n>We investigate the impact of vendor diversity by comparing Single-LLM, Single-Vendor, and Mixed-Vendor Multi-Agent Conversation (MAC) frameworks.
• Score: 6.913124180936944
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• FRAC-MAS: A Safe and Explainable Multi-Agent System for Fracture Diagnosis [0.6351973754158782]
  FRAC-MAS is an agentic AI system for automated, explainable, and safe bone fracture detection.<n>A pipeline-depth ablation study confirms that our multi-agent critic triages 86.6% of cases into a high-confidence auto-confirmed cohort.<n>Patient preference studies against Llama, MedGemma, and Gemini demonstrate significantly more comprehensible clinical reports.
  arXiv  Detail & Related papers  (2026-08-22T10:56:00Z)
• Why Specialist Models Still Matter: A Heterogeneous Multi-Agent Paradigm for Medical Artificial Intelligence [11.420145886356709]
  HetMedAgent is a heterogeneous medical multi-agent framework that enables conflict-aware evidence fusion, uncertainty-based clinician intervention triggering, and adaptive threshold calibration.<n> Experiments on three real-world clinical decision-making tasks demonstrate that the synergy between generalist LLMs and domain-specific specialist models significantly outperforms using either type of model alone.<n>HetMedAgent represents a shift from building medical LLMs or foundation models to multi-agent collaboration, achieving a balance between general reasoning capabilities and domain-specific precision.
  arXiv  Detail & Related papers  (2026-05-28T10:42:44Z)
• BLUEmed: Retrieval-Augmented Multi-Agent Debate for Clinical Error Detection [1.620466780389133]
  We introduce BLUEmed, a multi-agent debate framework augmented with hybrid Retrieval-Augmented Generation (RAG)<n>Bluemed decomposes each clinical note into focused sub-queries, retrieves source-partitioned evidence through dense, sparse, and online retrieval, and assigns two domain expert agents distinct knowledge bases to produce independent analyses.<n>We evaluate BLUEmed on a clinical terminology substitution detection benchmark under both zero-shot and few-shot prompting with multiple backbone models spanning proprietary and open-source families.
  arXiv  Detail & Related papers  (2026-04-12T00:30:31Z)
• XrayClaw: Cooperative-Competitive Multi-Agent Alignment for Trustworthy Chest X-ray Diagnosis [0.8880611506199769]
  XrayClaw is a novel framework that operationalizes multi-agent alignment through a sophisticated cooperative-competitive architecture.<n>XrayClaw integrates four specialized cooperative agents to simulate a systematic clinical workflow, alongside a competitive agent that serves as an independent auditor.<n>Our results indicate that XrayClaw effectively mitigates cumulative hallucinations and enhances the overall reliability of automated CXR diagnosis.
  arXiv  Detail & Related papers  (2026-04-03T03:39:30Z)
• One Panel Does Not Fit All: Case-Adaptive Multi-Agent Deliberation for Clinical Prediction [10.760929240872564]
  We propose CAMP (Case-Adaptive Multi-agent Panel), where an attending-physician agent dynamically assembles a specialist panel tailored to each case's diagnostic uncertainty.<n>A hybrid router directs each diagnosis through strong consensus, fallback to the attending physician's judgment, or evidence-based arbitration that weighs argument quality over vote counts.<n> CAMP consistently outperforms strong baselines while consuming fewer tokens than most competing multi-agent methods, with voting records and arbitration traces offering transparent decision audits.
  arXiv  Detail & Related papers  (2026-03-31T18:00:34Z)
• MedCoRAG: Interpretable Hepatology Diagnosis via Hybrid Evidence Retrieval and Multispecialty Consensus [24.19892707167392]
  Existing AI approaches for clinical diagnosis often lack transparency, structured reasoning, and deployability.<n>We propose MedCoRAG, an end-to-end framework that generates diagnostic hypotheses from standardized abnormal findings.<n>It then constructs a patient-specific evidence package by jointly retrieving and pruning UMLS knowledge graph paths and clinical guidelines.
  arXiv  Detail & Related papers  (2026-03-05T12:58:45Z)
• MMedExpert-R1: Strengthening Multimodal Medical Reasoning via Domain-Specific Adaptation and Clinical Guideline Reinforcement [63.82954136824963]
  Medical Vision-Language Models excel at perception tasks with complex clinical reasoning required in real-world scenarios.<n>We propose a novel reasoning MedVLM that addresses these challenges through domain-specific adaptation and guideline reinforcement.
  arXiv  Detail & Related papers  (2026-01-16T02:32:07Z)
• Collaborative Multi-Agent Test-Time Reinforcement Learning for Reasoning [112.16686518063456]
  We introduce textbfMulti-Agent Test-Time Reinforcement Learning (MATTRL), a framework that injects structured textual experience into multi-agent deliberation at inference time.<n>MATTRL forms a multi-expert team of specialists for multi-turn discussions, retrieves and integrates test-time experiences, and reaches consensus for final decision-making.<n>Across challenging benchmarks in medicine, math, and education, MATTRL improves accuracy by an average of 3.67% over a multi-agent baseline, and by 8.67% over comparable single-agent baselines
  arXiv  Detail & Related papers  (2026-01-14T17:57:43Z)
• Mediator-Guided Multi-Agent Collaboration among Open-Source Models for Medical Decision-Making [18.640622974004724]
  A blind combination of diverse vision-language models (VLMs) can amplify an erroneous outcome interpretation.<n>We propose MedOrch, a mediator-guided multi-agent collaboration framework for medical multimodal decision-making.<n>We show that the collaboration within distinct VLM-based agents can surpass the capabilities of any individual agent.
  arXiv  Detail & Related papers  (2025-08-08T04:02:10Z)
• On Arbitrary Predictions from Equally Valid Models [49.56463611078044]
  Model multiplicity refers to multiple machine learning models that admit conflicting predictions for the same patient.<n>We show that even small ensembles can mitigate/eliminate predictive multiplicity in practice.
  arXiv  Detail & Related papers  (2025-07-25T16:15:59Z)
• The Optimization Paradox in Clinical AI Multi-Agent Systems [13.177792688650971]
  The relationship between component-level optimization and system-wide performance remains poorly understood.<n>We evaluated this relationship using 2,400 real patient cases from the MIMIC-CDM dataset.<n>Our results reveal a paradox: while multi-agent systems generally outperformed single agents, the component-optimized or Best of Breed system with superior components and excellent process metrics significantly underperformed in diagnostic accuracy (67.7% vs. 77.4% for a top multi-agent system)
  arXiv  Detail & Related papers  (2025-06-06T23:01:51Z)
• MMedAgent-RL: Optimizing Multi-Agent Collaboration for Multimodal Medical Reasoning [63.63542462400175]
  We propose MMedAgent-RL, a reinforcement learning-based multi-agent framework that enables dynamic, optimized collaboration among medical agents.<n> Specifically, we train two GP agents based on Qwen2.5-VL via RL: the triage doctor learns to assign patients to appropriate specialties, while the attending physician integrates the judgments from multi-specialists.<n>Experiments on five medical VQA benchmarks demonstrate that MMedAgent-RL not only outperforms both open-source and proprietary Med-LVLMs, but also exhibits human-like reasoning patterns.
  arXiv  Detail & Related papers  (2025-05-31T13:22:55Z)
• Silence is Not Consensus: Disrupting Agreement Bias in Multi-Agent LLMs via Catfish Agent for Clinical Decision Making [80.94208848596215]
  We present a new concept called Catfish Agent, a role-specialized LLM designed to inject structured dissent and counter silent agreement.<n>Inspired by the catfish effect'' in organizational psychology, the Catfish Agent is designed to challenge emerging consensus to stimulate deeper reasoning.
  arXiv  Detail & Related papers  (2025-05-27T17:59:50Z)
• HiddenBench: Assessing Collective Reasoning in Multi-Agent LLMs via Hidden Profile Tasks [12.203366267017737]
  We introduce HiddenBench, the first benchmark for evaluating collective reasoning in multi-agent LLMs.<n>To ground the benchmark, we formalize the paradigm with custom tasks and show that GPT-4.1 groups fail to integrate distributed knowledge.<n>We then construct the full benchmark, spanning 65 tasks drawn from custom designs, prior human studies, and automatic generation.
  arXiv  Detail & Related papers  (2025-05-15T19:22:54Z)
• Ambiguous Medical Image Segmentation using Diffusion Models [60.378180265885945]
  We introduce a single diffusion model-based approach that produces multiple plausible outputs by learning a distribution over group insights. Our proposed model generates a distribution of segmentation masks by leveraging the inherent sampling process of diffusion. Comprehensive results show that our proposed approach outperforms existing state-of-the-art ambiguous segmentation networks.
  arXiv  Detail & Related papers  (2023-04-10T17:58:22Z)

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.