Cognitive Models and AI Algorithms Provide Templates for Designing Language Agents

TL;DR

This paper explores how cognitive models and AI algorithms can serve as blueprints for designing modular, interpretable language agents by formalizing agent templates and surveying existing designs.

Contribution

It formalizes agent templates inspired by cognitive science and AI, and surveys existing language agents to highlight their underlying design principles.

Findings

Existing language agents are based on templates derived from cognitive models and AI algorithms.

Formalization of agent templates clarifies how to compose multiple LLMs effectively.

Survey of literature reveals diverse design patterns rooted in cognitive science.

Abstract

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.