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

arXiv: https://arxiv.org/abs/2603.04421 · HTML: https://mlsanity.com/paper/2603.04421/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use.
- Builds on 7 of its 35 references that are in the map.
- First posted on arXiv 14 Feb 2026.

## Placed in

- LLM agents and tool use / [Medical and scientific domain agents](https://mlsanity.com/agents/medical-and-scientific-domain-agents/)

## Builds on (most cited first, 7 of 7)

- [Capabilities of Gemini Models in Medicine](https://mlsanity.com/paper/2404.18416/) (2024)
- [RareBench: Can LLMs Serve as Rare Diseases Specialists?](https://mlsanity.com/paper/2402.06341/) (2024)
- [MAM: Modular Multi-Agent Framework for Multi-Modal Medical Diagnosis via Role-Specialized Collaboration](https://mlsanity.com/paper/2506.19835/) (2025)
- [X-MAS: Towards Building Multi-Agent Systems with Heterogeneous LLMs](https://mlsanity.com/paper/2505.16997/) (2025)
- [Automated Clinical Problem Detection from SOAP Notes using a Collaborative Multi-Agent LLM Architecture](https://mlsanity.com/paper/2508.21803/) (2025)
- [Combining Insights From Multiple Large Language Models Improves Diagnostic Accuracy](https://mlsanity.com/paper/2402.08806/) (2024)
- [The Alignment Paradox of Medical Large Language Models in Infertility Care: Decoupling Algorithmic Improvement from Clinical Decision-making Quality](https://mlsanity.com/paper/2511.18084/) (2025)

## Built on by (most cited first, 2 of 2)

- [Multi-LLM Query Optimization](https://mlsanity.com/paper/2603.24617/) (2026)
- [Deliberative multi-agent large language models improve clinical reasoning in ophthalmology](https://mlsanity.com/paper/2603.21447/) (2026)

## Abstract (arXiv)

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.