超越联邦学习：面向自演化临床智能的去中心化智能体系统
Beyond Federated Learning: Decentralized Agentic Systems for Self-Evolving Clinical Intelligence
AI 导读
一篇 arXiv 观点文章提出 Decentralized Agentic Systems（DAS）框架，主张医疗 AI 从数据聚合转向经验聚合。与联邦学习在同类模型架构间平均数值梯度不同，DAS 让跨医疗机构的分布式 AI 智能体共享结构化的临床推理记录，即观察、假设、工具调用与结果反馈构成的诊断经验序列，并探讨其架构原则、部署、治理与开放挑战。
正文 · 原文
Abstract:Clinical expertise is inherently distributed: it resides not in any single dataset or institution but in the accumulated reasoning experiences of thousands of clinicians navigating diverse patient populations, resource constraints, and evolving treatment protocols. Yet current approaches to scaling medical AI, from centralized large language models to federated learning, remain anchored to a data-centric paradigm that treats knowledge as static parameters to be aggregated. In this Perspective, we argue for a fundamental shift from data aggregation to experience aggregation. We propose Decentralized Agentic Systems (DAS), a framework in which distributed AI agents operating across healthcare institutions synthesize collective clinical intelligence by sharing abstracted reasoning trajectories rather than raw data or model parameters. Unlike federated learning, which averages numerical gradients across homogeneous model architectures, DAS exchanges structured records of clinical reasoning, specifically the sequence of observations, hypotheses, tool invocations, and outcome feedback that constitute diagnostic experience. We examine the architectural principles, deployment considerations, governance requirements, and critical open challenges of this framework, laying the groundwork for a collaborative medical AI ecosystem where distributed expertise autonomously adapts to the complexities of longitudinal patient care.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.35453 [cs.AI] |
| (or arXiv:2610.35453v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.35453 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Haoyuan Li [view email]
[v1]
Mon, 26 Oct 2026 13:50:33 UTC (2,486 KB)
来源：arXiv cs.AI · arxiv.org