A Taxonomy of Architecture Options for Foundation Model-based Agents: Analysis and Decision Model
Jingwen Zhou, Qinghua Lu, Jieshan Chen, Liming Zhu, Xiwei Xu, Zhenchang Xing, Stefan Harrer
TL;DR
This paper addresses the fragmentation in foundation-model-based agent architectures by developing a structured taxonomy and a complementary decision model. It combines a systematic literature review, grey literature, and thematic coding to categorize functional capabilities and non-functional qualities, yielding a comprehensive design framework. The main contributions are the detailed taxonomy across input modalities, model access, external capabilities, planning, action, reflection, learning, and governance, plus a decision model to guide design-time and run-time decisions. The framework supports standardized comparisons, robust design choices, and scalable, ethically guided agent deployments in real-world settings.
Abstract
The rapid advancement of AI technology has led to widespread applications of agent systems across various domains. However, the need for detailed architecture design poses significant challenges in designing and operating these systems. This paper introduces a taxonomy focused on the architectures of foundation-model-based agents, addressing critical aspects such as functional capabilities and non-functional qualities. We also discuss the operations involved in both design-time and run-time phases, providing a comprehensive view of architectural design and operational characteristics. By unifying and detailing these classifications, our taxonomy aims to improve the design of foundation-model-based agents. Additionally, the paper establishes a decision model that guides critical design and runtime decisions, offering a structured approach to enhance the development of foundation-model-based agents. Our contributions include providing a structured architecture design option and guiding the development process of foundation-model-based agents, thereby addressing current fragmentation in the field.