HomeResearch LibraryCognitive Architectures for Language Agents
theoretical frameworkChapter 2TMLR · 2023

Cognitive Architectures for Language Agents

Theodore Sumers (Princeton), Shunyu Yao (Princeton), Karthik Narasimhan (Princeton)

Abstract

We draw on the rich history of cognitive science and symbolic AI to propose CoALA, a conceptual framework for language agents. CoALA organizes memory, action, and decision-making into a coherent architecture.

Key Contributions

  • →CoALA cognitive architecture framework
  • →Memory taxonomy for agents
  • →Action space categorization
Eigenvector Commentary

CoALA is the most rigorous theoretical framework for agent architecture design. It provides a vocabulary for discussing agent capabilities that is grounded in cognitive science — essential for enterprise architects who need to reason about what agents can and cannot do.

Topics

cognitive architectureagent designmemorydecision-making