EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Supervised agentic AI for precision oncology

Christoph F. Kurz, Tatiana Merzhevich, Bjoern M. Eskofier, Jacqueline Lammert, Benjamin Gmeiner

Discover Oncology · 04.11.2026 · 17 (1)

DOI: 10.1007/s12672-026-06237-w ↗

Kurz gefasst

Fachartikel in der Zeitschrift Discover Oncology, online erschienen am 04.11.2026. Verfasst von Christoph F. Kurz und 4 weiteren Autor:innen. Die Arbeit nennt 76 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Agentic artificial intelligence could transform precision oncology, particularly in molecularly heterogeneous diseases like breast cancer, by integrating multimodal data and rapidly evolving evidence, but probabilistic models clash with the deterministic requirements of cancer care. We describe a Supervisory Reference Architecture that separates specialized worker agents from an oversight meta-agent, enforces traceable reasoning, and enables auditability and regulatory accountability. This framework reframes evaluation around reasoning traces and supervisory interventions. We present it as a conceptual reference architecture rather than a validated system: no implementation, simulation, or empirical evaluation is reported.

Zitieren

APA

Kurz, C. F., Merzhevich, T., Eskofier, B. M., Lammert, J., & Gmeiner, B. (2026). Supervised agentic AI for precision oncology. Discover Oncology, 17(1). https://doi.org/10.1007/s12672-026-06237-w

Vancouver

Kurz CF, Merzhevich T, Eskofier BM, Lammert J, Gmeiner B. Supervised agentic AI for precision oncology. Discover Oncology. 2026;17(1). doi:10.1007/s12672-026-06237-w

BibTeX
@article{Kurz2026,
  author = {Kurz, Christoph F. and Merzhevich, Tatiana and Eskofier, Bjoern M. and Lammert, Jacqueline and Gmeiner, Benjamin},
  title = {Supervised agentic AI for precision oncology},
  journal = {Discover Oncology},
  year = {2026},
  volume = {17},
  number = {1},
  doi = {10.1007/s12672-026-06237-w}
}
Kostenlos starten →