Intelligence as Managed Autonomy: Failure, Escalation, and Governance for Agentic AI Systems

The paper introduces the SMARt (Self-Managing Multi-tier Autonomous Reasoning with Regulated/Revoked transitions) model, a four-layer framework designed to manage the autonomy of AI systems by detecting epistemic drift and enabling controlled operational adjustments. It presents a timed, guarded Petri net formulation that establishes formal properties for escalation and governance, addressing the architectural vulnerabilities associated with unbounded autonomy. This work is significant for practitioners as it provides a structured approach to ensure reliability and safety in autonomous AI deployments across various domains, including healthcare and robotics.