Metraipolis › archive › dc_8f5fb07ce83e

Bounded Autonomy and Verifiable Safety for Agentic AI Enabled Automation — arXiv:2610.08815

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.08815
License (as archived)
CC0-1.0
Archived
2026-10-08T11:56:05.646Z
SHA-256 of the archived text
b200a16b3a529ff452cbeebf6aa7352610684fde999845cd448d88e8b2d03262
Stable URL of this page
https://metraipolis.com/documento/dc_8f5fb07ce83e

How to cite

Bounded Autonomy and Verifiable Safety for Agentic AI Enabled Automation — arXiv:2610.08815 — arXiv (en), https://arxiv.org/abs/2610.08815 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8f5fb07ce83e (Metraipolis archive dc_8f5fb07ce83e, sha256 b200a16b3a529ff452cbeebf6aa7352610684fde999845cd448d88e8b2d03262)
BibTeX
@misc{dc8f5fb07ce83e,
  title = {Bounded Autonomy and Verifiable Safety for Agentic AI Enabled Automation — arXiv:2610.08815},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.08815},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8f5fb07ce83e; sha256 b200a16b3a529ff452cbeebf6aa7352610684fde999845cd448d88e8b2d03262},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.08815. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Agentic AI-enabled automation cannot be safely deployed in high-stakes environments on probabilistic reasoning alone. A recurring risk is epistemic drift: as reasoning deepens, system behavior may move away from subject-matter-expert constraints for safe operation. This paper presents BRaVeS, a bounded reasoning and safety-governance framework termed the Defensible Next-Gen Reasoning System (DNRS). BRaVeS encodes SME-defined constraints as invariant anchors, proposes MoDA-Style (Mixture of Depths Attention) depth-aware access as a candidate mechanism for keeping these anchors visible during inference, and uses a state hierarchy (SMARtAutonomy) to reduce autonomy as epistemic risk increases. To formalize bounded recovery, we introduce the Lyapunov-Bounded Consensus Framework (LBCF), which maps continuous epistemic-risk signals into a finite K-bag abstraction and applies shielded state transitions that enforce Lyapunov-style energy descent or route the system to a human-mediated terminal state. The formal convergence result applies to the finite LBCF abstraction under fixed thresholds and feasible-shield assumptions; it does not prove safety of the full continuous neural activation space. We evaluate the framework through a discrete event Monte Carlo simulation using HAI 22.04 industrial-control-system time-series data with synthetic noise and sensor-degradation regimes. Across the tested parameter-grouping strategies and thresholds, the LBCF process achieved finite-step convergence and no safety-guard violations. These results provide simulation-based evidence that bounded governance behavior can be enforced under the stated abstraction, while motivating future work on deployed transformer implementations, live human-in-the-loop validation, and broader adversarial settings.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Emerging Technologies (cs.ET); Systems and Control (eess.SY).
Pagina del lavoro: https://arxiv.org/abs/2610.08815 — 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 2026-10-08T10:50:37.623Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).