Agent Design Pattern Catalogue: A Collection of Architectural Patterns for Foundation Model based Agents

TL;DR

A pattern catalogue consisting of 18 architectural patterns with analyses of the context, forces, and trade-offs as the outcomes from the previous literature review is presented and a decision model for selecting the patterns is proposed.

Abstract

Foundation model-enabled generative artificial intelligence facilitates the development and implementation of agents, which can leverage distinguished reasoning and language processing capabilities to takes a proactive, autonomous role to pursue users' goals. Nevertheless, there is a lack of systematic knowledge to guide practitioners in designing the agents considering challenges of goal-seeking (including generating instrumental goals and plans), such as hallucinations inherent in foundation models, explainability of reasoning process, complex accountability, etc. To address this issue, we have performed a systematic literature review to understand the state-of-the-art foundation model-based agents and the broader ecosystem. In this paper, we present a pattern catalogue consisting of 18 architectural patterns with analyses of the context, forces, and trade-offs as the outcomes from the previous literature review. We propose a decision model for selecting the patterns. The proposed catalogue can provide holistic guidance for the effective use of patterns, and support the architecture design of foundation model-based agents by facilitating goal-seeking and plan generation.

Figures (19)

• Figure 1: Methodology.
• Figure 2: Ecosystem of FM-based agent systems annotated with architectural patterns in gray boxes.
• Figure 3: Passive goal creator.
• Figure 4: Proactive goal creator.
• Figure 5: Prompt/response optimiser.