# Can A Cognitive Architecture Fundamentally Enhance LLMs? Or Vice Versa?

arXiv: https://arxiv.org/abs/2401.10444 · HTML: https://mlsanity.com/paper/2401.10444/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Jan 2024.

## Built on by (most cited first, 9 of 9)

- [Prompting Techniques for Reducing Social Bias in LLMs through System 1 and System 2 Cognitive Processes](https://mlsanity.com/paper/2404.17218/) (2024)
- [Towards Rationality in Language and Multimodal Agents: A Survey](https://mlsanity.com/paper/2406.00252/) (2024)
- [CAIM: Development and Evaluation of a Cognitive AI Memory Framework for Long-Term Interaction with Intelligent Agents](https://mlsanity.com/paper/2505.13044/) (2025)
- [Psychology of Artificial Intelligence: Epistemological Markers of the Cognitive Analysis of Neural Networks](https://mlsanity.com/paper/2407.09563/) (2024)
- [Analyzing the Roles of Language and Vision in Learning from Limited Data](https://mlsanity.com/paper/2403.19669/) (2024)
- [TRIZ Agents: A Multi-Agent LLM Approach for TRIZ-Based Innovation](https://mlsanity.com/paper/2506.18783/) (2025)
- [Computational Multi-Agents Society Experiments: Social Modeling Framework Based on Generative Agents](https://mlsanity.com/paper/2508.17366/) (2025)
- [Automated stereotactic radiosurgery planning using a human-in-the-loop reasoning large language model agent](https://mlsanity.com/paper/2512.20586/) (2025)
- [Polysemy of Synthetic Neurons Towards a New Type of Explanatory Categorical Vector Spaces](https://mlsanity.com/paper/2505.07831/) (2025)

## Abstract (arXiv)

The paper discusses what is needed to address the limitations of current LLM-centered AI systems. The paper argues that incorporating insights from human cognition and psychology, as embodied by a computational cognitive architecture, can help develop systems that are more capable, more reliable, and more human-like. It emphasizes the importance of the dual-process architecture and the hybrid neuro-symbolic approach in addressing the limitations of current LLMs. In the opposite direction, the paper also highlights the need for an overhaul of computational cognitive architectures to better reflect advances in AI and computing technology. Overall, the paper advocates for a multidisciplinary, mutually beneficial approach towards developing better models both for AI and for understanding the human mind.