Guardado en:
Detalles Bibliográficos
Autores principales: Eslami, Ali, Yu, Jiangbo
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2603.10779
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915888781852672
author Eslami, Ali
Yu, Jiangbo
author_facet Eslami, Ali
Yu, Jiangbo
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2603_10779
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle A Control-Theoretic Foundation for Agentic Systems
Eslami, Ali
Yu, Jiangbo
Systems and Control
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.
title A Control-Theoretic Foundation for Agentic Systems
topic Systems and Control
url https://arxiv.org/abs/2603.10779