HomeResearch LibraryCognitive Architectures for Language Agents
Chapter 1 · 2023

Cognitive Architectures for Language Agents

Theodore R. Sumers, Shunyu Yao, Karthik Narasimhan

Abstract

We propose a unifying framework for language agents drawing on cognitive science, organizing agents around memory, action, and decision-making components.

Eigenvector Insight — Zone III / PASF-PADE AnalysisNot part of the original paper
Eigenvector Research — Marco van Hurne
How this paper contributes to solving the Zone III problem (PASF-PADE)

This paper provides the theoretical foundation for Zone III agent design. By mapping agent components to cognitive science concepts — working memory, long-term memory, procedural memory — it gives enterprise architects a vocabulary for designing agent systems that mirror how humans handle complex, long-running tasks. The framework's action taxonomy (memory manipulation, process execution, UI interaction) maps directly to enterprise workflow components.

Why AI is not sufficient for Zone III without this

Zone III refers to high-complexity, high-risk, long-running agentic workflows — the class of enterprise AI deployments where a single failure can cascade across hundreds of steps. Standard AI models, trained to predict the next token, are not inherently designed for durable, governed, multi-step execution. This paper addresses one or more of the structural gaps that make Zone III deployments unsafe without explicit architectural intervention.

Topics

cognitive architecturememorydecision-makingagent design