The Containment Gap: How Deployed Agentic AI Frameworks Fail Public-Facing Safety Requirements
Agentic large language model systems that autonomously invoke tools, maintain persistent memory, and execute multi-step plans are increasingly deployed in public-facing domains, including government services, healthcare triage, and financial advising. We ask whether the frameworks used to build these systems provide architectural-level structural safety guarantees. Applying six containment principles derived from a compositional model of agentic architectures, we audit three dominant frameworks
Record details
Published: 11 June 2026
Source: arXiv
Category: Research
Topics: Healthcare · Agents & autonomy · Transparency
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.
Auditing LLM-Governed Social Robots with Culture-Specific Moral Gradients
arXiv · 2 June 2026
SURGENT: A Surgical Multi-Agent Assistance System Across the Perioperative Workflow
arXiv · 28 May 2026
Clinical Harness for Governable Medical AI Skill Ecosystems
arXiv · 25 June 2026
SEVA: Self-Evolving Verification Agent with Process Reward for Fact Attribution
arXiv · 29 June 2026
Always-OnAgents:A Survey of Persistent Memory, State, and Governance in LLMAgents
arXiv · 29 June 2026
What Does the AI Doctor Value? Auditing Pluralism in the Clinical Ethics of Language Models
arXiv · 18 May 2026
How to cite this record
ethics.ai (11 June 2026), “The Containment Gap: How Deployed Agentic AI Frameworks Fail Public-Facing Safety Requirements,” evidence record 1123, https://ethics.ai/record/1123 (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.