Metraipolis › archive › dc_e586ffd09ce0

FedReady: Bounded Agents for Federation Formation — arXiv:2611.03586

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.03586
License (as archived): CC0-1.0
Archived: 2026-11-03T10:39:49.383Z
SHA-256 of the archived text: ebe09399b54335362d1e097ee8081e7a3e1bcad10ea3d7daed1bc742eda522f6
Stable URL of this page: https://metraipolis.com/documento/dc_e586ffd09ce0

How to cite

FedReady: Bounded Agents for Federation Formation — arXiv:2611.03586 — arXiv (en), https://arxiv.org/abs/2611.03586 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e586ffd09ce0 (Metraipolis archive dc_e586ffd09ce0, sha256 ebe09399b54335362d1e097ee8081e7a3e1bcad10ea3d7daed1bc742eda522f6)

BibTeX

@misc{dce586ffd09ce0,
  title = {FedReady: Bounded Agents for Federation Formation — arXiv:2611.03586},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.03586},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e586ffd09ce0; sha256 ebe09399b54335362d1e097ee8081e7a3e1bcad10ea3d7daed1bc742eda522f6},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.03586. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Multiagent Systems (cs.MA).
Pagina del lavoro: https://arxiv.org/abs/2611.03586 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-03T10:39:34.956Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).