Securing Agentic AI: From Per-Action Checks to Trajectory Assurance
Autonomous agents are increasingly used to execute consequential tasks in environments governed by operational constraints, organizational policies, regulatory requirements, and technical standards. Their safety is therefore determined not by the correctness of individual actions, but by whether their overall behavior remains consistent with the rules and invariants of the systems in which they operate. As large language model (LLM)-based agents become more autonomous and increasingly delegate t
Record details
Published: 3 August 2026
Source: arXiv
Category: Research
Topics: Regulation · Agents & autonomy · Environment
Retrieved: 4 August 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.
Heterogeneous Multi-Agent Reinforcement Learning for Radio Resource Management under Coupled Finite-Horizon Constraints
arXiv fairness query · 3 August 2026
AtumAI: A Principled Framework for Agentic Generation of Datacenter Control-Plane Policies
arXiv cs.AI · 3 August 2026
Beyond Component Testing: Validating Agentic AI Systems
arXiv cs.AI · 31 July 2026
MAGA: Multi-Platform Self-Fusion of GUI Agents via Structured Action Distillation
arXiv cs.AI · 31 July 2026
EnvACE: Internalizing Environment Dynamics via World Rehearsal for Agentic Reinforcement Learning
HuggingFace Daily Papers · 5 August 2026
On-Policy and Off-Policy Learning for Large Action Spaces
arXiv cs.AI · 30 July 2026
How to cite this record
ethics.ai (3 August 2026), “Securing Agentic AI: From Per-Action Checks to Trajectory Assurance,” evidence record 15910, https://ethics.ai/record/15910 (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.