Metraipolis › archive › dc_659107e7eef8
Engineering Reliable Commit Gates for Agentic AI: Cost-Aware Verification Portfolios under Common-Mode Data Failures — arXiv:2609.10969
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.10969
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T05:57:33.338Z
- SHA-256 of the archived text
750c6370eb9f8021e1f40cf95dcf4a9ae2e89538b69535bdd730bb3a4d4bb001- Stable URL of this page
https://metraipolis.com/documento/dc_659107e7eef8
How to cite
Engineering Reliable Commit Gates for Agentic AI: Cost-Aware Verification Portfolios under Common-Mode Data Failures — arXiv:2609.10969 — arXiv (en), https://arxiv.org/abs/2609.10969 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_659107e7eef8 (Metraipolis archive dc_659107e7eef8, sha256 750c6370eb9f8021e1f40cf95dcf4a9ae2e89538b69535bdd730bb3a4d4bb001)
BibTeX
@misc{dc659107e7eef8,
title = {Engineering Reliable Commit Gates for Agentic AI: Cost-Aware Verification Portfolios under Common-Mode Data Failures — arXiv:2609.10969},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.10969},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_659107e7eef8; sha256 750c6370eb9f8021e1f40cf95dcf4a9ae2e89538b69535bdd730bb3a4d4bb001},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.10969. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Agentic systems commit state-changing actions, but additional verifiers can inherit the same upstream fault. We present VP-CONTROL, a runtime-assurance design and deterministic benchmark for cost-aware commit gates. Its 48 task templates yield 2,880 scenarios across six fault regimes. A fixed-call 2 x 2 experiment separates verifier-model diversity from evidence-source diversity. On frozen proposals from two local actor families, a cross-model vote over shared evidence approves 62.9% of unsafe proposals, versus 22.9% with an independent source. The source effect is 40.9 percentage points, compared with 11.3 for model diversity. A portfolio controller selects verification plans using only deployment-observable metadata. Approximate cluster-adjusted calibration at a nominal 5% per-task target yields 1.9% unsafe execution and 38.2% automated safe coverage on the locked test. Matched-budget portfolios also improve on fixed verification policies. Transfer remains conditional: unseen fault families yield 16-26% risk, and a FinQA check fails to reproduce the source effect with the tested small verifiers. A preregistered live HTTP/SQLite study tests concurrent writes and lost responses. After-check races defeat verifier-only gates; transactional partial guards prevent only covered failures, while a full atomic guard records no unsafe effects across 216 episodes. Idempotent request identifiers prevent duplicate effects after lost responses. The results motivate explicit evidence lineage, cost-aware selection, and commit-time enforcement, while exposing the limits of approximate calibration and local-tool generalization. Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-09-11 in cs.SE). Categorie arXiv: Software Engineering (cs.SE). Pagina del lavoro: https://arxiv.org/abs/2609.10969 — 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 2026-10-16T05:45:13.287Z dalla pagina https://arxiv.org/catchup/cs.SE/2026-09-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).