Agentic AI Safety: A Structured Review of Open Problems and Their Regulatory Anchoring
AI · 04.08.2026 · 7 (8) · 298
DOI: 10.3390/ai7080298 ↗Kurz gefasst
Fachartikel in der Zeitschrift AI, online erschienen am 04.08.2026. Verfasst von Tomáš Valenta und 2 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 112 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministry of Industry and Trade of the Czech Republic.
Abstract (Originalsprache)
The shift from passive predictive models to autonomous agents capable of tool use and multi-step planning moves the AI safety landscape from prediction error to control failure: small misjudgements become irreversible actions, and risks compound across long horizons and populations of interacting systems. We present a structured review and taxonomy of open scientific problems in agentic AI safety, mapped explicitly onto the EU AI Act and the NIST AI Risk Management Framework. The corpus follows a PRISMA-ScR scoping review, assembled through anchor-based citation chaining and curated reading lists across arXiv, the major machine-learning conferences, and selected security and fairness venues, with a primary March 2026 search cut-off (extended to May 2026 during revision for a small number of high-relevance governance and agentic-safety sources), explicit eligibility criteria, and an analytical distinction between open scientific problems and deployment risks. The taxonomy identifies eight problem families spanning reinforcement-learning policies and language-model planners: goal specification, inner alignment, safe learning and robustness, scalable oversight, interpretability, tool-use security, multi-agent safety, and evaluation and assurance. Mapping these onto the two frameworks shows close alignment for some families and notable absences for others, with multi-agent safety surfacing as a regulatory gap. We add a per-family research roadmap with concrete milestones and a practitioner-facing deployment-posture triage, arguing that progress on inner alignment, interpretability for deceptive-alignment detection, and multi-agent safety would most directly reduce compliance uncertainty.
Förderung
- Ministry of Industry and Trade of the Czech Republic
Zitieren
APA
Valenta, T., Rozinek, O., & Horálek, J. (2026). Agentic AI Safety: A Structured Review of Open Problems and Their Regulatory Anchoring. AI, 7(8), 298. https://doi.org/10.3390/ai7080298
Vancouver
Valenta T, Rozinek O, Horálek J. Agentic AI Safety: A Structured Review of Open Problems and Their Regulatory Anchoring. AI. 2026;7(8):298. doi:10.3390/ai7080298
BibTeX
@article{Valenta2026,
author = {Valenta, Tomáš and Rozinek, Ondřej and Horálek, Josef},
title = {Agentic AI Safety: A Structured Review of Open Problems and Their Regulatory Anchoring},
journal = {AI},
year = {2026},
volume = {7},
number = {8},
pages = {298},
doi = {10.3390/ai7080298}
}
EUVIMED