Metraipolis › archive › dc_2daffeed2273

A Policy Algebra for Trust-Preserving Agentic AI Execution — arXiv:2608.16402

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.16402
License (as archived): CC0-1.0
Archived: 2026-10-18T17:44:36.140Z
SHA-256 of the archived text: cfb26eea865cb2bb71ee0bce634d425b775c6c345ceba9fa055eb106b6c54d19
Stable URL of this page: https://metraipolis.com/documento/dc_2daffeed2273

How to cite

A Policy Algebra for Trust-Preserving Agentic AI Execution — arXiv:2608.16402 — arXiv (en), https://arxiv.org/abs/2608.16402 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2daffeed2273 (Metraipolis archive dc_2daffeed2273, sha256 cfb26eea865cb2bb71ee0bce634d425b775c6c345ceba9fa055eb106b6c54d19)

BibTeX

@misc{dc2daffeed2273,
  title = {A Policy Algebra for Trust-Preserving Agentic AI Execution — arXiv:2608.16402},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.16402},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2daffeed2273; sha256 cfb26eea865cb2bb71ee0bce634d425b775c6c345ceba9fa055eb106b6c54d19},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.16402. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language model-based agentic frameworks primarily optimize capability: whether an agent can reason, retrieve information, call tools, delegate work, and complete a goal. Enterprise execution requires a stronger property. A successful result is not reliable if it was produced through unauthorized data access, widened delegated authority, unapproved side effects, unrecoverable budget consumption, or incomplete evidence. This paper defines reliable capability as a path property: an agent is reliably capable only when it completes a task through action events that remain admissible under identity, profile, tool, data, memory, budget, artifact, approval, and audit constraints. We propose a policy algebra that defines the reliability envelope within which agent capability may be exercised. Security profiles and runtime obligations compose through joins, intersections, budget narrowing, approval inheritance, and evidence accumulation; the resulting composition is both trust-preserving and the least restrictive state satisfying all governing inputs. The algebra also propagates restrictions across multi-agent calls and introduces cost-aware artifact materialization, which redirects open-ended execution toward a recoverable outcome as budget exposure grows. The evaluation is interpreted as a reliability-capability trade-off rather than a capability benchmark: the policy-algebra runtime intervenes on 94.8% of policy-violating events while retaining an 86.9% task-completion rate, eliminates the observed profile-monotonicity and zero-artifact-exhaustion violations, and increases audit completeness to 98.6%. The method provides researchers and practitioners with formal correctness conditions, executable decision semantics, and trace evidence for building agents that are not only capable, but reliably capable.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.16402 — 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 2026-10-18T16:29:13.867Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).