FedReady Uses Bounded LLM Agents for Federated Learning Formation
Original title: FedReady: Bounded Agents for Federation Formation
FedReady prepares task-specific data for federated learning with LLM agents and digest-checked contracts.
Federated learning requires repeated federation formation for new studies. FedReady employs bounded LLM agents to propose contracts, adapters, and task code. Site discovery prioritizes recall and eligibility verification removes false positives. It supports 39 simulated sites and four tasks with minimal performance impact versus manual preparation.
- Recall reaches 1.00 at precision 0.65
- Local verification removes 17 false positives
- 45,575 task-record instances supported
- Maximum survival-curve difference is 0.001133
From the original article
1 min read at arxiv.orgFederated 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.
By Ziyue Xu · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.