A Control-Theoretic Foundation for Agentic Systems

TL;DR

This paper introduces a control-theoretic framework for analyzing and designing agentic AI systems with hierarchical decision-making capabilities embedded within feedback control loops, emphasizing safety and adaptability.

Contribution

It formalizes agency as hierarchical runtime decision authority within control systems, extending traditional models to include dynamic reconfiguration and adaptation.

Findings

Defines a five-level hierarchy of agency in control systems.

Shows increasing agency introduces complex dynamical behaviors.

Provides design constraints for safe AI control architectures.

Abstract

This paper develops a control-theoretic framework for analyzing agentic systems embedded within feedback control loops, where an AI agent may adapt controller parameters, select among control strategies, invoke external tools, reconfigure decision architectures, and modify control objectives during operation. These capabilities are formalized by interpreting agency as hierarchical runtime decision authority over elements of the control architecture, leading to an augmented closed-loop representation in which physical states, internal memory, tool outputs, interaction signals, and design variables evolve as a coupled dynamical system. A five-level hierarchy of agency is defined, ranging from fixed control laws to runtime synthesis of control architectures and objectives. The analysis shows that increasing agency introduces interacting dynamical mechanisms such as time-varying adaptation, endogenous switching, decision-induced delays, and structural reconfiguration. The framework is developed in both nonlinear and linear settings, providing explicit design constraints for AI-enabled control systems in safety-critical applications.