FedReady: Bounded Agents for Federation Formation
arXiv cs.AI · 3 Nov 2026, 04:32 AEST
FedReady is a system designed to streamline federation formation in federated learning by utilizing bounded LLM agents. It enhances the process of selecting task-eligible sites and preparing local data for federated training or analysis.
Key facts
- 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.
- We present FedReady, a system that performs federation formation with bounded LLM agents.
- Candidate site discovery prioritizes recall; local eligibility verification checks task support before site admission.
- 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.
- These results establish the feasibility of task-specific data preparation before ordinary FL training or analysis.
Read aloud
FedReady is a system designed to streamline federation formation in federated learning by utilizing bounded L L M agents. It enhances the process of selecting task-eligible sites and preparing local data for federated training or analysis. 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. We present FedReady, a system that performs federation formation with bounded L L M agents. Candidate site discovery prioritizes recall; local eligibility verification checks task support before site admission. Across thirty nine simulated retinal sites and four tasks, discovery reaches recall one point zero zero at precision zero point six five; local eligibility verification removes all seventeen false positives without losing an eligible site-task pair. These results establish the feasibility of task-specific data preparation before ordinary FL training or analysis.
Sources in this cluster
- FedReady: Bounded Agents for Federation Formation
arXiv cs.AI · 3 Nov 2026, 04:32 AEST