A Taxonomy of Architecture Options for Foundation Model-based Agents: Analysis and Decision Model
This work addresses the fragmentation in designing foundation-model-based agents for AI developers and researchers, though it is incremental as it organizes existing knowledge rather than proposing new methods.
This paper tackles the challenge of designing and operating foundation-model-based agent systems by introducing a taxonomy that classifies architectural options and a decision model to guide design and runtime decisions, aiming to unify and improve development in this fragmented field.
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.