MediHive: A Decentralized Agent Collective for Medical Reasoning 事件

MediHive: A Decentralized Agent Collective for Medical Reasoning arXiv:2603.27150v2 Announce Type: replace 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 po