Agentic Design Patterns: A System-Theoretic Framework

TL;DR

This paper introduces a rigorous system-theoretic framework for designing robust agentic AI systems, decomposing them into core subsystems and providing 12 reusable design patterns to address common challenges.

Contribution

It presents a novel system-theoretic architecture and a set of 12 agentic design patterns, offering a structured methodology for building reliable and modular AI agents.

Findings

Framework applied to ReAct, improving its architecture.

Patterns help address systemic deficiencies in agent design.

Enhanced understanding and standardization of agentic system design.

Abstract

With the development of foundation model (FM), agentic AI systems are getting more attention, yet their inherent issues like hallucination and poor reasoning, coupled with the frequent ad-hoc nature of system design, lead to unreliable and brittle applications. Existing efforts to characterise agentic design patterns often lack a rigorous systems-theoretic foundation, resulting in high-level or convenience-based taxonomies that are difficult to implement. This paper addresses this gap by introducing a principled methodology for engineering robust AI agents. We propose two primary contributions: first, a novel system-theoretic framework that deconstructs an agentic AI system into five core, interacting functional subsystems: Reasoning & World Model, Perception & Grounding, Action Execution, Learning & Adaptation, and Inter-Agent Communication. Second, derived from this architecture and directly mapped to a comprehensive taxonomy of agentic challenges, we present a collection of 12 agentic design patterns. These patterns - categorised as Foundational, Cognitive & Decisional, Execution & Interaction, and Adaptive & Learning - offer reusable, structural solutions to recurring problems in agent design. The utility of the framework is demonstrated by a case study on the ReAct framework, showing how the proposed patterns can rectify systemic architectural deficiencies. This work provides a foundational language and a structured methodology to standardise agentic design communication among researchers and engineers, leading to more modular, understandable, and reliable autonomous systems.