MediHive: A Decentralized Agent Collective for Medical Reasoning
Xiaoyang Wang, Christopher C. Yang · 2026
Read MediHive: A Decentralized Agent Collective for Medical Reasoning by Xiaoyang Wang, Christopher C. Yang (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13522319.txt.
Description
Xiaoyang Wang and Christopher C Yang introduced MediHive, a decentralized team of AI agents for medical reasoning. Published in 2026, the framework answers medical questions with language-model agents that pick their own roles, analyze first, debate where evidence diverges, and fuse peer insights over rounds toward agreement. Single agents often stumble on tangled, cross-disciplinary problems, while centrally run teams bottleneck and fail at one point.
MediHive beat single-model and centralized baselines on two medical question sets, scoring about 84 percent on MedQA and about 78 percent on PubMedQA. A shared memory pool plus iterative fusion gives the system scale and fault tolerance without a boss agent. The authors pitch it for reasoning-heavy medical tasks where uncertainty and conflicting evidence are the norm. Readers get a design that trades central control for resilient collaboration.
Catalog record
| CREATOR | Xiaoyang Wang, Christopher C. Yang |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 60 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |