Bounded Autonomy and Verifiable Safety for Agentic AI Enabled Automation
Journal of Intelligent & Robotic Systems · 22.09.2026 · 112 (4)
DOI: 10.1007/s10846-026-02467-w ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Intelligent & Robotic Systems, online erschienen am 22.09.2026. Verfasst von Srini Ramaswamy und 1 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
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.
Zitieren
APA
Ramaswamy, S., & Nayak, D. (2026). Bounded Autonomy and Verifiable Safety for Agentic AI Enabled Automation. Journal of Intelligent & Robotic Systems, 112(4). https://doi.org/10.1007/s10846-026-02467-w
Vancouver
Ramaswamy S, Nayak D. Bounded Autonomy and Verifiable Safety for Agentic AI Enabled Automation. Journal of Intelligent & Robotic Systems. 2026;112(4). doi:10.1007/s10846-026-02467-w
BibTeX
@article{Ramaswamy2026,
author = {Ramaswamy, Srini and Nayak, Deveeshree},
title = {Bounded Autonomy and Verifiable Safety for Agentic AI Enabled Automation},
journal = {Journal of Intelligent & Robotic Systems},
year = {2026},
volume = {112},
number = {4},
doi = {10.1007/s10846-026-02467-w}
}
EUVIMED