Agents

Cognitive Architectures for Language Agents (CoALA)

First page

Paper summary

Princeton proposes CoALA, a systematic framework for understanding and building language agents.

Ask this paper

Key points

Production-system inspiration: Draws on classical cognitive architectures and production systems (Soar, ACT-R) to structure language agents.

Four-component organization: Agents consist of memory modules, action space, decision procedures, and reasoning - each with specific design choices.

Unifies recent methods: Catalogs methods for LLM-based reasoning, grounding, learning, and decision-making as instantiations of CoALA components.

Design-space map: Makes the language-agent design space explicit, helping researchers compare systems and identify underexplored combinations.

Every Monday