arXiv Machine Learning
Bounded Autonomy and Verifiable Safety for Agentic AI Enabled Automation
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Jun 12
Intelligence as Managed Autonomy: Failure, Escalation, and Governance for Agentic AI Systems
arXiv:2605. 27628v2 Announce Type: replace Abstract: As autonomous and agentic AI systems scale in robotic and human-machine environments, managing hallucination and persistent but unjustified action remains an open challenge.
arXiv AI
Jul 2
Managed Autonomy at Runtime: Gear-Based Safety and Governance for Single- and Multi-Agent Cyber-Physical Systems
arXiv:2607. 00334v1 Announce Type: new Abstract: Autonomous agents, whether LLM-driven software agents or robotic physical agents, face a common class of failure modes when operating without continuous human oversight: safety violations from unverified actions, behavioral instability from unconstrained loops, and continuity loss from unhandled error states.
arXiv AI
Jun 16
Minimal Oversight: Uncertainty-Aware Governance for Delegated AI Systems
arXiv:2606. 15563v1 Announce Type: new Abstract: AI systems increasingly delegate decisions to specialized models, evaluators, tools, and supervisory controllers.
arXiv AI
Jul 31
Towards Trustworthy Embodied Intelligence: A Systems Framework and Graded Trustworthiness Levels
arXiv:2607. 26121v1 Announce Type: cross Abstract: Embodied intelligence integrates learned perception and decision making with real-time computation, control, and physical interaction.
arXiv AI
Jun 8
Agentic Physical AI toward a Domain-Specific Foundation Model for Energy Systems: A Case Study on Nuclear Reactor Control
arXiv:2512. 23292v5 Announce Type: replace Abstract: The prevailing paradigm in AI for physical systems: scaling general-purpose foundation models toward universal multimodal reasoning, confronts a barrier at the control interface.
arXiv AI
Jul 22
From Agent Failure Paths to Quantified Residual Risk: A Compositional Framework for Resilient Agentic AI
arXiv:2607. 18243v1 Announce Type: new Abstract: Agentic AI is crossing trust boundaries faster than current risk models can represent.