Cognitive Architectures for Language Agents

TL;DR

This paper introduces CoALA, a systematic framework inspired by cognitive science to organize, analyze, and guide the development of language agents with modular memory, structured actions, and decision-making processes.

Contribution

It proposes the CoALA framework, integrating cognitive science principles into language agent design, and provides a retrospective and prospective analysis of the field.

Findings

CoALA effectively organizes existing language agent research.

Identifies key components for advancing language agent capabilities.

Outlines future directions for more general and capable language-based AI.

Abstract

Recent efforts have augmented large language models (LLMs) with external resources (e.g., the Internet) or internal control flows (e.g., prompt chaining) for tasks requiring grounding or reasoning, leading to a new class of language agents. While these agents have achieved substantial empirical success, we lack a systematic framework to organize existing agents and plan future developments. In this paper, we draw on the rich history of cognitive science and symbolic artificial intelligence to propose Cognitive Architectures for Language Agents (CoALA). CoALA describes a language agent with modular memory components, a structured action space to interact with internal memory and external environments, and a generalized decision-making process to choose actions. We use CoALA to retrospectively survey and organize a large body of recent work, and prospectively identify actionable directions towards more capable agents. Taken together, CoALA contextualizes today's language agents within the broader history of AI and outlines a path towards language-based general intelligence.