Cognitive Models and AI Algorithms Provide Templates for Designing Language Agents
This paper provides a conceptual framework for researchers and developers seeking to design more effective and interpretable language agents by leveraging existing knowledge from cognitive science and AI.
This paper proposes that cognitive models and AI algorithms can serve as blueprints for designing modular language agents, addressing the challenge of combining multiple large language models (LLMs) for complex tasks. It formalizes the concept of an 'agent template' and surveys existing language agents, demonstrating how their designs are rooted in these established models.
While contemporary large language models (LLMs) are increasingly capable in isolation, there are still many difficult problems that lie beyond the abilities of a single LLM. For such tasks, there is still uncertainty about how best to take many LLMs as parts and combine them into a greater whole. This position paper argues that potential blueprints for designing such modular language agents can be found in the existing literature on cognitive models and artificial intelligence (AI) algorithms. To make this point clear, we formalize the idea of an agent template that specifies roles for individual LLMs and how their functionalities should be composed. We then survey a variety of existing language agents in the literature and highlight their underlying templates derived directly from cognitive models or AI algorithms. By highlighting these designs, we aim to call attention to agent templates inspired by cognitive science and AI as a powerful tool for developing effective, interpretable language agents.