A Theory of Least Autonomy in AI

Jul 14, 2026

Researchers propose 'least autonomy' as a generalization of the least privilege principle for agentic AI systems. They introduce a compositional blast radius and a directed agent influence graph to measure and control the autonomy of AI agents. The theory includes mechanisms to detect authorization composition, decision manipulation, and cross-domain capability composition.

Why it matters: This work provides a formal framework for controlling AI agent autonomy, addressing safety risks in multi-agent and enterprise systems.

Full story at: arXiv AI/ML ↗