Metraipolis › archive › dc_3e4423dbdc53
Trustworthy Execution of Industrial Agents — arXiv:2611.02300
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.02300
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T10:49:33.207Z
- SHA-256 of the archived text
1b41bfaba53c1d9a5a93027ef1345f2894e9dcf26f834fd1db4dcb0b467bb733- Stable URL of this page
https://metraipolis.com/documento/dc_3e4423dbdc53
How to cite
Trustworthy Execution of Industrial Agents — arXiv:2611.02300 — arXiv (en), https://arxiv.org/abs/2611.02300 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3e4423dbdc53 (Metraipolis archive dc_3e4423dbdc53, sha256 1b41bfaba53c1d9a5a93027ef1345f2894e9dcf26f834fd1db4dcb0b467bb733)
BibTeX
@misc{dc3e4423dbdc53,
title = {Trustworthy Execution of Industrial Agents — arXiv:2611.02300},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.02300},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3e4423dbdc53; sha256 1b41bfaba53c1d9a5a93027ef1345f2894e9dcf26f834fd1db4dcb0b467bb733},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02300. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Industrial agents increasingly modify persistent engineering objects rather than merely generate answers. Authentication and successful calls cannot establish whether intended changes occurred, evidence supports a conclusion, or historical results remain applicable. We present a framework for trustworthy industrial-agent execution within a single enterprise governance domain. Eight control domains assign responsibilities across authority, planning, composition, tool execution, actual effects, evidence, baseline and use governance, and recovery and evolution. A four-plane architecture and three control chains connect these responsibilities through typed objects and version-bound interfaces. The specification separates tool returns from actual engineering effects, evidence coverage from engineering judgment, and historical lifecycle state from current applicability. Multi-agent handoffs are an architectural extension examined through deterministic interface tests. Distinct prototypes examine selected mechanisms using conformance tests, ablations, uncertainty stress, CAD/CAE execution, and local persistence. An OpenFOAM fixture produces COMPLETE coverage with FAIL judgment; an expired-job case requires readmission despite completed computation. CAD and recovery counterexamples expose omitted mandatory checks, discarded negative facts, and inconsistent producer-consumer mappings. Targeted repairs support local regression conclusions. The reported 0/29 hazardous commits measure closed-set specification conformance, not a safety probability. We distinguish the complete framework, implemented paths, and empirical evidence, identifying check-inventory completeness and cross-module fact preservation as prerequisites for extending these results. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno). Categorie arXiv: Software Engineering (cs.SE) ; Multiagent Systems (cs.MA). Pagina del lavoro: https://arxiv.org/abs/2611.02300 — 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 2026-11-03T10:49:22.887Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).