AI ethics evidence index Search
Source-linked daily record
Evidence record 7010 · automatically gathered

Agent Control Protocol: Admission Control for Agent Actions

Autonomous agents can produce harmful behavioral patterns from individually valid requests -- a threat class per-request policy evaluation cannot address, because stateless engines evaluate each request in isolation. We present ACP, a temporal admission control protocol enforcing behavioral properties over execution traces via static risk scoring combined with stateful signals (anomaly accumulation, cooldown) through a LedgerQuerier abstraction. ACP blocks execution based on deterministic, histo

Record details

Published: 19 March 2026
Source: arXiv
Category: Research
Topics: Regulation · Agents & autonomy
Retrieved: 14 July 2026

source-onlyevidence status

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.

Same publisher byline · Shared topic: Regulation

From Admission to Invariants: Measuring Deviation in Delegated Agent Systems

arXiv · 19 April 2026

Same publisher byline · Shared topic: Regulation

Atomic Decision Boundaries: A Structural Requirement for Guaranteeing Execution-Time Admissibility in Autonomous Systems

arXiv · 19 April 2026

Shared topic: Regulation · Shared topic: Agents & autonomy

I Can't Believe It's Corrupt: Evaluating Corruption in Multi-Agent Governance Systems

arXiv · 19 March 2026

Shared topic: Regulation · Shared topic: Agents & autonomy

Security, privacy, and agentic AI in a regulatory view: From definitions and distinctions to provisions and reflections

arXiv · 19 March 2026

Shared topic: Regulation · Shared topic: Agents & autonomy

Soft-Label Governance for Distributional Safety in Multi-Agent Systems

arXiv · 19 March 2026

Shared topic: Regulation · Shared topic: Agents & autonomy

MemArchitect: A Policy Driven Memory Governance Layer

arXiv · 18 March 2026

How to cite this record

ethics.ai (19 March 2026), “Agent Control Protocol: Admission Control for Agent Actions,” evidence record 7010, https://ethics.ai/record/7010 (originally published by arXiv).

JSON

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.