Metraipolis › archive › dc_1f752fb8b433

Reliability Engineering for AI Systems: Challenges, Methods, and Directions — arXiv:2609.35316

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.35316
License (as archived)
CC0-1.0
Archived
2026-10-07T20:58:42.837Z
SHA-256 of the archived text
1960fd7d65be1fde99769129115876e472abd17729417cee7ba52726efd94dfe
Stable URL of this page
https://metraipolis.com/documento/dc_1f752fb8b433

How to cite

Reliability Engineering for AI Systems: Challenges, Methods, and Directions — arXiv:2609.35316 — arXiv (en), https://arxiv.org/abs/2609.35316 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_1f752fb8b433 (Metraipolis archive dc_1f752fb8b433, sha256 1960fd7d65be1fde99769129115876e472abd17729417cee7ba52726efd94dfe)
BibTeX
@misc{dc1f752fb8b433,
  title = {Reliability Engineering for AI Systems: Challenges, Methods, and Directions — arXiv:2609.35316},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.35316},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_1f752fb8b433; sha256 1960fd7d65be1fde99769129115876e472abd17729417cee7ba52726efd94dfe},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.35316. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

AI reliability concerns whether an AI system performs its intended function dependably over a stated period and under stated operating conditions, with stated evidence. As these systems become more autonomous, that function includes more than a correct output. Retrieval, memory, tool use, permissions, human oversight, and interactions among systems must operate consistently and safely, and, for generative systems, so must the reasoning process that produces the output. Average benchmark accuracy measures capability; it does not quantify this broader reliability claim. This paper adapts established reliability engineering methods, from failure definitions and operational envelopes to FMEA, accelerated testing, field monitoring, and reliability growth, to AI systems. A four-level diagnostic framework classifies failures as component, operational-loop, agentic-conduct, or network and governance failures. Test, evaluation, verification, and validation (TEVV), sequential monitoring, and FRACAS create and refresh evidence. SMART provides statistical guidance for measurement, analysis, assessment, and test planning; the NIST AI Risk Management Framework provides organizational guidance for governance, evaluation, monitoring, and mitigation. Three cases illustrate the program: adversarial testing of a convolutional neural network, perception-error propagation, and autonomous-vehicle disengagements. Established reliability engineering provides a usable foundation; new measurements and safety guardrails are still needed as these systems are self-evolving.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Applications (stat.AP).
Pagina del lavoro: https://arxiv.org/abs/2609.35316 — 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 2026-10-07T20:29:01.835Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).