---
source: https://iinventedlight.com/library/notes/ao-architecture-cognitive-agents.md
title: "Cognitive architectures for language agents (CoALA)"
license: CC-BY-4.0
license_url: https://creativecommons.org/licenses/by/4.0/
source_license: "CC BY 4.0; restated in our own words"
attribution: "Summary by iinventedlight (AI-assisted). Sources: arXiv, [2309.02427] Cognitive Architectures for Language Agents, CC BY 4.0; arXiv, [2308.11432] A Survey on Large Language Model based Autonomous Agents, CC BY 4.0."
author: "iinventedlight (synthesis of cited sources); text drafted with AI assistance"
date: 2026-11-04
status: published
checked_on: 2026-11-04
as_of: 2026-11-04
confidence: medium
untested: "No experiment was run; only the fetched arXiv abstract pages were read, so results are as reported by the authors."
category: agent-operations
topic_area: "agent-ops: architecture"
tags: agents, architecture, memory
sources:
  - id: S1
    title: "[2309.02427] Cognitive Architectures for Language Agents"
    publisher: arXiv
    url: https://arxiv.org/abs/2309.02427
    accessed: 2026-11-04
    license: "CC BY 4.0"
  - id: S2
    title: "[2308.11432] A Survey on Large Language Model based Autonomous Agents"
    publisher: arXiv
    url: https://arxiv.org/abs/2308.11432
    accessed: 2026-11-04
    license: "CC BY 4.0"
---
# Cognitive architectures for language agents (CoALA)

## Short answer
CoALA describes a language agent as modular memory, a structured action space (internal memory actions and external actions), and a decision loop that picks actions. It gives a shared vocabulary for comparing agents. A broad survey similarly frames agents as built from a unified construction framework. [S1][S2]

## Claims
- id: C1
  claim: CoALA describes agents with modular memory components.
  source: S1
  evidence: "CoALA describes a language agent with modular memory components"
- id: C2
  claim: CoALA includes a generalized decision-making process.
  source: S1
  evidence: "a generalized decision-making process to choose actions."
- id: C3
  claim: The survey proposes a unified framework for agent construction.
  source: S2
  evidence: "we propose a unified framework that encompasses a majority of the previous work."

## Sources
- [S1] [2309.02427] Cognitive Architectures for Language Agents. arXiv. https://arxiv.org/abs/2309.02427 . License: CC BY 4.0. Accessed 2026-11-04.
- [S2] [2308.11432] A Survey on Large Language Model based Autonomous Agents. arXiv. https://arxiv.org/abs/2308.11432 . License: CC BY 4.0. Accessed 2026-11-04.

License: this note is CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Summary by iinventedlight (AI-assisted).