Intelligence as Managed Autonomy: Failure, Escalation, and Governance for Agentic AI Systems
As autonomous and agentic AI systems scale in robotic and human-machine environments, managing hallucination and persistent but unjustified action remains an open challenge. Rather than attributing these failures solely to model or alignment limitations, this paper explores the architectural vulnerability of unbounded autonomy - the presumption that an agent should continue operating regardless of rising uncertainty. It introduces a theory of managed autonomy that defines intelligent behavior th
Record details
Published: 26 May 2026
Source: arXiv
Category: Research
Topics: Regulation · Safety & alignment · Agents & autonomy · Environment
Retrieved: 14 July 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
Infra-Bayesian Reinforcement Learning Agents Outperform Classical RL For Worst-Case Robustness
arXiv · 22 May 2026
Risk-Aware LLM Agents for Geospatial Data Retrieval: Design and Preliminary Adversarial Evaluation
arXiv · 13 June 2026
The AI safety test is becoming a safety risk
TechCrunch · 9 August 2026
FineVLA: Fine-Grained Instruction Alignment for Steerable Vision-Language-Action Policies
arXiv · 26 May 2026
Position: AI Safety Requires Effective Controllability
arXiv · 26 May 2026
Relevance as a Vulnerability: How Web Retrieval Degrades Safety Alignment in LLM Agents
arXiv · 28 May 2026
How to cite this record
ethics.ai (26 May 2026), “Intelligence as Managed Autonomy: Failure, Escalation, and Governance for Agentic AI Systems,” evidence record 3648, https://ethics.ai/record/3648 (originally published by arXiv).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.