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.

翻译：基础模型赋能的生成式人工智能促进了智能体的开发与实现，这些智能体能够利用卓越的推理与语言处理能力，以主动、自主的角色追求用户目标。然而，目前缺乏系统化的知识来指导从业者在设计智能体时应对目标追寻（包括生成工具性目标与规划）所面临的挑战，例如基础模型固有的幻觉问题、推理过程的可解释性、复杂的责任归属等。为解决这一问题，我们开展了系统性文献综述，以理解当前基于基础模型的智能体及其更广泛生态系统的最新进展。本文提出了一个包含18个架构模式的模式目录，其中结合了先前文献综述的成果，对每种模式的上下文背景、作用力及权衡取舍进行了分析。我们提出了一个用于模式选择的决策模型。该目录能够为模式的有效运用提供整体性指导，并通过促进目标追寻与规划生成，支持基于基础模型的智能体架构设计。