vix.ing · top · new · best · stats

Cognitive Architectures for Language Agents

2023/09/05 by Theodore R. Sumers, Sumers, Theodore R., Shunyu Yao +5 · 4 voices · 124 citations
Computer Science · Psychology · Social Sciences · #Action (physics) #Artificial intelligence #Chaining #Cognition #Cognitive science #Computer science #Data science #Knowledge management #Language and cultural evolution #Modular design #Natural Language Processing Techniques #Process (computing) #Programming language #Psychology #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2309.02427

published in arXiv (Cornell University) (Cornell University)

openalex publication_date 2023/09/05 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/29

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.

Cited by

Discussions

Related