Towards Responsible Generative AI: A Reference Architecture for Designing Foundation Model based Agents
This work provides guidance for designing responsible AI agents, but it is incremental as it builds on existing agent frameworks without introducing a new paradigm.
The paper tackles the lack of systematic exploration in architecture design for foundation model-based agents and addresses responsible AI concerns like security and accountability by proposing a pattern-oriented reference architecture, which is evaluated for completeness and utility by mapping it to two real-world agents.
Foundation models, such as large language models (LLMs), have been widely recognised as transformative AI technologies due to their capabilities to understand and generate content, including plans with reasoning capabilities. Foundation model based agents derive their autonomy from the capabilities of foundation models, which enable them to autonomously break down a given goal into a set of manageable tasks and orchestrate task execution to meet the goal. Despite the huge efforts put into building foundation model based agents, the architecture design of the agents has not yet been systematically explored. Also, while there are significant benefits of using agents for planning and execution, there are serious considerations regarding responsible AI related software quality attributes, such as security and accountability. Therefore, this paper presents a pattern-oriented reference architecture that serves as guidance when designing foundation model based agents. We evaluate the completeness and utility of the proposed reference architecture by mapping it to the architecture of two real-world agents.