MediHive: A Decentralized Agent Collective for Medical Reasoning

TL;DR

MediHive introduces a decentralized multi-agent framework for medical question answering that improves scalability, resilience, and reasoning accuracy over traditional centralized systems.

Contribution

It presents a novel decentralized multi-agent system with shared memory and iterative fusion, enhancing fault tolerance and performance in medical AI reasoning tasks.

Findings

Outperforms single-LLM and centralized baselines on MedQA and PubMedQA datasets.

Achieves 84.3% and 78.4% accuracy on MedQA and PubMedQA respectively.

Demonstrates superior reasoning capabilities in complex medical questions.

Abstract

Large language models (LLMs) have revolutionized medical reasoning tasks, yet single-agent systems often falter on complex, interdisciplinary problems requiring robust handling of uncertainty and conflicting evidence. Multi-agent systems (MAS) leveraging LLMs enable collaborative intelligence, but prevailing centralized architectures suffer from scalability bottlenecks, single points of failure, and role confusion in resource-constrained environments. Decentralized MAS (D-MAS) promise enhanced autonomy and resilience via peer-to-peer interactions, but their application to high-stakes healthcare domains remains underexplored. We introduce MediHive, a novel decentralized multi-agent framework for medical question answering that integrates a shared memory pool with iterative fusion mechanisms. MediHive deploys LLM-based agents that autonomously self-assign specialized roles, conduct initial analyses, detect divergences through conditional evidence-based debates, and locally fuse peer insights over multiple rounds to achieve consensus. Empirically, MediHive outperforms single-LLM and centralized baselines on MedQA and PubMedQA datasets, attaining accuracies of 84.3% and 78.4%, respectively. Our work advances scalable, fault-tolerant D-MAS for medical AI, addressing key limitations of centralized designs while demonstrating superior performance in reasoning-intensive tasks.