Agent Design Pattern Catalogue: A Collection of Architectural Patterns for Foundation Model based Agents
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.
Cite
@article{arxiv.2405.10467,
title = {Agent Design Pattern Catalogue: A Collection of Architectural Patterns for Foundation Model based Agents},
author = {Yue Liu and Sin Kit Lo and Qinghua Lu and Liming Zhu and Dehai Zhao and Xiwei Xu and Stefan Harrer and Jon Whittle},
journal= {arXiv preprint arXiv:2405.10467},
year = {2024}
}