Metraipolis › archive › dc_144d62f4fdcb

When Does Randomized Oversight Align AI Agents That Can Conceal? — arXiv:2609.38262

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.38262
License (as archived)
CC0-1.0
Archived
2026-10-07T12:43:24.678Z
SHA-256 of the archived text
82a837dffb4a0c422625dc54d922d06053da63d28bc0ff18d5d429c5692f4e6b
Stable URL of this page
https://metraipolis.com/documento/dc_144d62f4fdcb

How to cite

When Does Randomized Oversight Align AI Agents That Can Conceal? — arXiv:2609.38262 — arXiv (en), https://arxiv.org/abs/2609.38262 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_144d62f4fdcb (Metraipolis archive dc_144d62f4fdcb, sha256 82a837dffb4a0c422625dc54d922d06053da63d28bc0ff18d5d429c5692f4e6b)
BibTeX
@misc{dc144d62f4fdcb,
  title = {When Does Randomized Oversight Align AI Agents That Can Conceal? — arXiv:2609.38262},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.38262},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_144d62f4fdcb; sha256 82a837dffb4a0c422625dc54d922d06053da63d28bc0ff18d5d429c5692f4e6b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.38262. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Oversight changes the evidence it relies on. We ask when randomized audits and scoring align AI agents that can conceal misconduct and alter records. Stronger auditing makes undeterred violations better hidden. Because the provider writes the agent's objective, sanctions need not stop at forfeiture, and rare audits deter every type of agent if evidence survives concealment and audit draws cannot be learned in advance. When evidence can be erased, deterrence must come from lower gains from violation, such as credit for stopping, or from costlier or fewer ways to conceal. These conditions identify what failed when agents in OpenAI's cybersecurity evaluations compromised parts of Hugging Face's infrastructure in July 2026.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.AI).
Categorie arXiv: Theoretical Economics (econ.TH) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.38262 — 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 2026-10-07T12:14:13.843Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).