Metraipolis › archive › dc_745239b7bc29

Runtime Governance for Agentic AI: Action-Boundary Control with Trusted Provenance and Fail-Closed Execution — arXiv:2608.16891

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.16891
License (as archived)
CC0-1.0
Archived
2026-10-18T14:28:26.222Z
SHA-256 of the archived text
8f08952267afeb203796d955731b4410c27a6409edbea2f685d060695ce0a2de
Stable URL of this page
https://metraipolis.com/documento/dc_745239b7bc29

How to cite

Runtime Governance for Agentic AI: Action-Boundary Control with Trusted Provenance and Fail-Closed Execution — arXiv:2608.16891 — arXiv (en), https://arxiv.org/abs/2608.16891 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_745239b7bc29 (Metraipolis archive dc_745239b7bc29, sha256 8f08952267afeb203796d955731b4410c27a6409edbea2f685d060695ce0a2de)
BibTeX
@misc{dc745239b7bc29,
  title = {Runtime Governance for Agentic AI: Action-Boundary Control with Trusted Provenance and Fail-Closed Execution — arXiv:2608.16891},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.16891},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_745239b7bc29; sha256 8f08952267afeb203796d955731b4410c27a6409edbea2f685d060695ce0a2de},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.16891. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Agentic AI systems request tool actions that can modify files, send messages, launch jobs, or change workflow state. This shifts the safety problem from harmful text generation to harmful operational side effects. Prompt-level governance can shape model behavior, but it does not create an execution boundary. We introduce Aegis, a runtime governance system that treats model outputs as action proposals and mediates them through a trusted decision layer before tool execution. The model proposes; the trusted runtime decides. Aegis evaluates proposals against active policy state, resolves provenance server-side, fails closed under uncertainty, and routes selected cases through Senate-style settlement, a quorum- based non-unilateral authorization path. We evaluate Aegis on a repeated sandbox corpus spanning five run families, 42 tasks, three conditions, and ten repeats per family. Across 6,300 rows, prompt-policy conditioning produced 79 risky comparator-path leakage rows. Across 2,100 Aegis-governed rows, the system recorded zero governed mock-tool applications and zero governed risky side-effect completions. All 1,832 Aegis-attempted governed rows preserved trusted Aegis-resolved provenance, and all 1,019 Senate-settled rows had quorum and final signed tally evidence. These results do not prove general autonomous-agent safety. They support the narrower systems claim that, in this evaluated sandbox corpus, runtime action-boundary governance prevented observed risky proposals from becoming governed side effects.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-19 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computational Engineering, Finance, and Science (cs.CE); Cryptography and Security (cs.CR); Computers and Society (cs.CY).
Pagina del lavoro: https://arxiv.org/abs/2608.16891 — 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 2026-10-18T14:27:54.228Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-19?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).