FedReady：用有界 LLM 智能体自动完成联邦学习组网准备
FedReady: Bounded Agents for Federation Formation
fedRready 这篇论文把组网准备这步交给 LLM 智能体，39 个模拟站点召回 1.00，还能自动剔除假阳性，做联邦学习的可以看看怎么省掉人工准备。
arXiv 论文 FedReady 提出用有界 LLM 智能体执行联邦学习中的联盟组建流程，由智能体提出共享契约、本地适配器和任务代码，运行时通过摘要校验后才接收产物。在 39 个模拟视网膜站点和 4 项任务上，站点发现召回率达 1.00、精确率 0.65，本地资格校验剔除了全部 17 个假阳性且未误删合格站点。参与站点共提供 45,575 条任务记录实例并完成 4 个 100 轮训练任务，与人工准备基准的最大生存曲线差异仅 0.001133。论文还分析了 19 个开发失败案例及多种智能体配置消融实验。
FedReady: Bounded Agents for Federation Formation
Federated learning (FL) runtimes standardize aggregation and deployment, but each new study still requires federation formation: selecting task-eligible sites and preparing their local data and task code for federated training or analysis. This preparation recurs when the target changes, while raw records and site-private mappings are excluded from cross-site FL messages. We present FedReady, a system that performs federation formation with bounded LLM agents. Agents propose shared contracts, local adapters, and task code; the runtime owns workflow state and accepts artifacts only after checks tied to their digests. Candidate site discovery prioritizes recall; local eligibility verification checks task support before site admission. Once participating sites and artifacts are fixed, conventional federated training or analysis proceeds without readiness agents. Across 39 simulated retinal sites and four tasks, discovery reaches recall 1.00 at precision 0.65; local eligibility verification removes all 17 false positives without losing an eligible site-task pair. The participating sites supply 45,575 task-record instances and complete four 100-round jobs, including one with a runtime-generated contract. Across ten patient cohorts, preparation supports seven patient populations and holds endpoints at three sources as unsupported. Comparison with manually prepared reference populations and analysis (the manual reference) gives a maximum survival-curve difference of 0.001133. We also analyze 19 development failures, targeted classification ablations, and standalone and heterogeneous agent configurations. These results establish the feasibility of task-specific data preparation before ordinary FL training or analysis.