From Admission to Invariants: Measuring Deviation in Delegated Agent Systems
Autonomous agent systems are governed by enforcement mechanisms that flag hard constraint violations at runtime. The Agent Control Protocol identifies a structural limit of such systems: a correctly-functioning enforcement engine can enter a regime in which behavioral drift is invisible to it, because the enforcement signal operates below the layer where deviation is measurable. We show that enforcement-based governance is structurally unable to determine whether an agent behavior remains within
Record details
Published: 19 April 2026
Source: arXiv
Category: Research
Topics: Regulation · Agents & autonomy
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.
Agent Control Protocol: Admission Control for Agent Actions
arXiv · 19 March 2026
Atomic Decision Boundaries: A Structural Requirement for Guaranteeing Execution-Time Admissibility in Autonomous Systems
arXiv · 19 April 2026
SafeAgent: A Runtime Protection Architecture for Agentic Systems
arXiv · 19 April 2026
Party Autonomy in Determining the Law Applicable to Non-contractual Obligations concerning Cross-Border Data Transfers
arXiv · 20 April 2026
From Craft to Kernel: A Governance-First Execution Architecture and Semantic ISA for Agentic Computers
arXiv · 20 April 2026
First, Do No Harm (With LLMs): Mitigating Racial Bias via Agentic Workflows
arXiv · 20 April 2026
How to cite this record
ethics.ai (19 April 2026), “From Admission to Invariants: Measuring Deviation in Delegated Agent Systems,” evidence record 5654, https://ethics.ai/record/5654 (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.