Metraipolis › archive › dc_aca197f60f5a
Five Primitives for Governing Autonomous AI Agents at Runtime — arXiv:2608.26696
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.26696
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T14:22:48.653Z
- SHA-256 of the archived text
cc2e1fb9f2af58c8eaee3fc43c4b2a3d4ee4fa2bbca466a652cbc507a091273f- Stable URL of this page
https://metraipolis.com/documento/dc_aca197f60f5a
How to cite
Five Primitives for Governing Autonomous AI Agents at Runtime — arXiv:2608.26696 — arXiv (en), https://arxiv.org/abs/2608.26696 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_aca197f60f5a (Metraipolis archive dc_aca197f60f5a, sha256 cc2e1fb9f2af58c8eaee3fc43c4b2a3d4ee4fa2bbca466a652cbc507a091273f)
BibTeX
@misc{dcaca197f60f5a,
title = {Five Primitives for Governing Autonomous AI Agents at Runtime — arXiv:2608.26696},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.26696},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_aca197f60f5a; sha256 cc2e1fb9f2af58c8eaee3fc43c4b2a3d4ee4fa2bbca466a652cbc507a091273f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.26696. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Enterprise deployments of autonomous AI agents inherit a control model built for human users and long-lived services, and the fit fails in three specific ways: agent principals are ephemeral, appearing and vanishing faster than provisioning; their actions are selected by a model rather than programmed, so the set of things they may attempt is not known in advance; and the population is discovered rather than provisioned, because anyone who can call an API can create one. We argue that governing such agents is a runtime problem -- not a model-alignment problem and not a build-time problem -- and we derive five primitives from the questions that must be answered before an action takes effect and after it has: discovery, identity, governance, attestation, and supply chain. For each we state what fails if it is absent and why the others cannot structurally supply it. We describe an implementation in which an agent's action is mediated against policy before it takes effect, authorised against a per-tenant action vocabulary, and recorded in a hash-linked signed ledger a third party can verify with the vendor out of the loop. We report what the architecture costs: the enforcement point sits on the request's critical path, identity requires a sidecar per workload, and fail-closed mediation converts availability incidents into denial. We are explicit about implementation status: four primitives are built and running in private pilots, and the fifth is built as separate tooling and not yet integrated into the request path. We keep it in the set deliberately: a five-part decomposition that exactly matches what its authors happened to build is not a taxonomy but a description of a codebase. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-28 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI) ; Cryptography and Security (cs.CR); Software Engineering (cs.SE). Pagina del lavoro: https://arxiv.org/abs/2608.26696 — 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 2026-10-17T13:16:53.507Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).