Conference paper
MediHive: A Decentralized Agent Collective for Medical Reasoning
IEEE International Conference on Healthcare Informatics (ICHI)
12 Aug 2026
Featured in Collection : Drexel's Newest Publications
Abstract
Single-agent large language models (LLMs) and centralized multi-agent systems (MAS) face scalability bottlenecks, single points of failure, and role confusion in medical reasoning. We propose MediHive, a decentralized multi-agent framework built around a passive shared memory pool. Agents self-assign specialist roles, debate conditionally when they disagree, and iteratively fuse peers’ analyses to reach consensus without a central coordinator. On MedQA and PubMedQA with a Llama-3.1-70B-Instruct backbone, MediHive reaches 84.3% and 78.4% accuracy, surpassing single-agent and centralized multi-agent baselines.
Metrics
1 Record Views
Details
- Title
- MediHive: A Decentralized Agent Collective for Medical Reasoning
- Creators
- Xiaoyang Wang - Drexel University, School of Computer and Information SciencesChristopher C Yang - Drexel University, Information Science
- Publication Details
- IEEE International Conference on Healthcare Informatics (ICHI)
- Conference
- 2026 IEEE 14th International Conference on Healthcare Informatics (ICHI), 14th (Minneapolis, Minnesota, United States, 01 Jun 2026–03 Jun 2026)
- Publisher
- IEEE
- Resource Type
- Conference paper
- Language
- English
- Academic Unit
- Information Science; School of Computer and Information Sciences
- Other Identifier
- 991022201158804721