Engineering Trustworthy Agentic AI for Critical Systems

Abstract

Agentic artificial intelligence systems, capable of autonomous perception, planning, tool use, and multi-step action, are increasingly proposed for critical engineering domains where decisions carry physical, operational, or economic consequences. This survey addresses a gap in current literature by treating trustworthiness, whether agentic behavior can be verified, audited, and trusted under the constraints that engineering practice actually requires, as a first-class engineering property, rath

Categories

Framework mappings

Suggested from the entry's categories.

@misc{alrefai2026engineering,
  title = {{Engineering Trustworthy Agentic AI for Critical Systems}},
  author = {Omar Al-Refai and Ibrahim Shahbaz and Adam Ali Husseinat and Michael Mandulak and Jaewon Kim and Eman Hammad},
  year = {2026},
  month = jul,
  eprint = {2607.18548},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2607.18548}
}