Metraipolis › archive › dc_98a5f8730cd6

AI Harness: Certification under Proposal-Conditioned Information for Foundation-Model Agents — arXiv:2609.32184

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.32184
License (as archived)
CC0-1.0
Archived
2026-10-07T20:55:10.240Z
SHA-256 of the archived text
006ffc40c04f71850798674a1c0e769eee1f0e4ced4b93ea17114af1c0c2bdc3
Stable URL of this page
https://metraipolis.com/documento/dc_98a5f8730cd6

How to cite

AI Harness: Certification under Proposal-Conditioned Information for Foundation-Model Agents — arXiv:2609.32184 — arXiv (en), https://arxiv.org/abs/2609.32184 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_98a5f8730cd6 (Metraipolis archive dc_98a5f8730cd6, sha256 006ffc40c04f71850798674a1c0e769eee1f0e4ced4b93ea17114af1c0c2bdc3)
BibTeX
@misc{dc98a5f8730cd6,
  title = {AI Harness: Certification under Proposal-Conditioned Information for Foundation-Model Agents — arXiv:2609.32184},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.32184},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_98a5f8730cd6; sha256 006ffc40c04f71850798674a1c0e769eee1f0e4ced4b93ea17114af1c0c2bdc3},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.32184. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Foundation-model agents are often modeled as policies over an observed state. In deployed systems, however, a runtime may intervene only after the model has emitted a semantic proposal, making the proposal both an action candidate and a decision-time observation generated by a history-conditioned process. We show that collapsing this structure into a state-only proposal envelope can preserve proposal coverage while destroying certifiability. In a finite robust interface, the viability kernel of the collapsed model is contained in the physical projection of the history-augmented kernel, and the collapse is lossless exactly when every proposal-conditioned collapsed fiber retains a common robust-safe intervention. This gap can be maximal even with constant-size proposal and history alphabets. The same common-action condition yields a dual result: observing the current proposal can restore robust feasibility when it separates latent modes requiring incompatible interventions. We extend these one-step results over time using exact finite beliefs and standard safety and reachability fixed points, separating indefinite operational viability from finite worst-case verified progress. Controlled model-in-the-loop tests reproduce the predicted obstructions when telemetry or effect verification is removed or intervention authority is restricted. Thus, our contribution is not a new fixed-point calculus, but a characterization of when proposal--history correlation at the model--tool boundary is necessary for certification.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Systems and Control (eess.SY).
Pagina del lavoro: https://arxiv.org/abs/2609.32184 — 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 2026-10-07T20:29:00.721Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).