EUVIMEDEUVIMED entdecken
Crossref

Starfish-FL: Harnessing Agentic Federated Analytics

Yunkai Bao, Zainab Saad, Farhan Abbas, Kaue Duarte, Tolulope Sajobi, Bijoy Menon, Jiayu Zhou, Steve Drew

ACM Transactions on Computing for Healthcare · 25.08.2026

DOI: 10.1145/3843774 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Computing for Healthcare, online erschienen am 25.08.2026. Verfasst von Yunkai Bao und 7 weiteren Autor:innen. Die Arbeit nennt 54 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Federated learning (FL) enables privacy-preserving multi-site clinical research, but orchestrating, monitoring, and interpreting federated analyses remains out of reach for the biostatisticians and clinicians who most need them. We present Starfish-FL, a multi-tier agent harness for cross-silo healthcare analytics built around the safety invariant that the LLM is advisory and cannot independently trigger consequential actions. Agents operate at three tiers. An Autonomous Experiment Agent orchestrates end-to-end experiments via CLI tools, an Embedded Router Agent handles adaptive aggregation, early stopping, and failure triage, and Controller Agent Hooks produce per-site summaries, outlier flags, and convergence signals. Three hybrid safety policies, SafeStop, SafeAggregate, and SafeTriage, gate every site exclusion, early stop, and recovery action behind deterministic preconditions, so LLM errors cannot cause unsafe state transitions, conditional on guard correctness. All agent features are opt-in and degrade gracefully to standard FL, and the platform provides 21 Python and R task implementations with built-in statistical diagnostics. Evaluated across four LLM providers with repeated-run confidence intervals, task selection reaches \({\sim}97\%\) accuracy with hosted models, the online SafeStop policy saves 50–70% of rounds with no accuracy loss, and safety-policy validation shows a 100% safe-action rate under injected failures, confirming that deterministic guards, not the LLM, preserve safety.

Zitieren

APA

Bao, Y., Saad, Z., Abbas, F., Duarte, K., Sajobi, T., Menon, B., Zhou, J., & Drew, S. (2026). Starfish-FL: Harnessing Agentic Federated Analytics. ACM Transactions on Computing for Healthcare. https://doi.org/10.1145/3843774

Vancouver

Bao Y, Saad Z, Abbas F, Duarte K, Sajobi T, Menon B, et al. Starfish-FL: Harnessing Agentic Federated Analytics. ACM Transactions on Computing for Healthcare. 2026. doi:10.1145/3843774

BibTeX
@article{Bao2026,
  author = {Bao, Yunkai and Saad, Zainab and Abbas, Farhan and Duarte, Kaue and Sajobi, Tolulope and Menon, Bijoy and Zhou, Jiayu and Drew, Steve},
  title = {Starfish-FL: Harnessing Agentic Federated Analytics},
  journal = {ACM Transactions on Computing for Healthcare},
  year = {2026},
  doi = {10.1145/3843774}
}
Kostenlos starten →