Enhancing Computational Cognitive Architectures with LLMs: A Case Study

2025-09-13

AI Summary

This study addresses the challenge of simultaneously achieving real-world complexity and psychological plausibility when integrating large language models (LLMs) with computational cognitive architectures. We propose a hybrid framework grounded in CLARION’s implicit–explicit dual-system architecture, enabling bidirectional information exchange and functional complementarity between LLMs and cognitive modules via modular interface design, prompt engineering, and in-context learning. To our knowledge, this is the first work to deeply embed LLMs within a classical cognitive architecture while preserving psychological validity. The integration significantly enhances reasoning, language understanding, and task generalization capabilities. Empirical evaluation demonstrates synergistic advantages in both computational efficiency and cognitive fidelity. Our approach establishes a novel paradigm for next-generation intelligent agents that jointly optimize high computational power and strong psychological validity.

Technology Category

• Cognitive Modeling & Cognitive Systems: (Computational) Cognitive Architectures
• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work

Abstract

Computational cognitive architectures are broadly scoped models of the human mind that combine different psychological functionalities (as well as often different computational methods for these different functionalities) into one unified framework. They structure them in a psychologically plausible and validated way. However, such models thus far have only limited computational capabilities, mostly limited by the computational tools and techniques that were adopted. More recently, LLMs have proved to be more capable computationally than any other tools. Thus, in order to deal with both real-world complexity and psychological realism at the same time, incorporating LLMs into cognitive architectures naturally becomes an important task. In the present article, a synergistic combination of the Clarion cognitive architecture and LLMs is discussed as a case study. The implicit-explicit dichotomy that is fundamental to Clarion is leveraged for a seamless integration of Clarion and LLMs. As a result, computational power of LLMs is combined with psychological nicety of Clarion.

Problem

• Enhancing cognitive architectures with LLMs
• Integrating LLMs into Clarion architecture
• Combining computational power with psychological realism

Innovation

• Integrating LLMs into Clarion cognitive architecture
• Leveraging implicit-explicit dichotomy for seamless integration
• Combining LLMs' power with psychological realism