# Cognitive LLMs: Towards Integrating Cognitive Architectures and Large Language Models for Manufacturing Decision-making

arXiv: https://arxiv.org/abs/2408.09176 · HTML: https://mlsanity.com/paper/2408.09176/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 14 of its 48 references that are in the map.
- First posted on arXiv 17 Aug 2024.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 14 of 14)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [A Survey on In-context Learning](https://mlsanity.com/paper/2301.00234/) (2022)
- [Using cognitive psychology to understand GPT-3](https://mlsanity.com/paper/2206.14576/) (2022)
- [Reinforcement learning](https://mlsanity.com/paper/2405.10369/) (2024)
- [Thinking Fast and Slow in Large Language Models](https://mlsanity.com/paper/2212.05206/) (2022)
- [Turning large language models into cognitive models](https://mlsanity.com/paper/2306.03917/) (2023)
- [Understanding In-Context Learning in Transformers and LLMs by Learning to Learn Discrete Functions](https://mlsanity.com/paper/2310.03016/) (2023)
- [Large Language Models Assume People are More Rational than We Really are](https://mlsanity.com/paper/2406.17055/) (2024)
- [Towards Generalizable Neuro-Symbolic Systems for Commonsense Question Answering](https://mlsanity.com/paper/1910.14087/) (2019)
- [Core Challenges in Embodied Vision-Language Planning](https://mlsanity.com/paper/2106.13948/) (2021)
- [Generalizable Neuro-symbolic Systems for Commonsense Question Answering](https://mlsanity.com/paper/2201.06230/) (2022)
- [Enabling High-Level Machine Reasoning with Cognitive Neuro-Symbolic Systems](https://mlsanity.com/paper/2311.07759/) (2023)

## Built on by (most cited first, 5 of 5)

- [Probing a Vision-Language-Action Model for Symbolic States and Integration into a Cognitive Architecture](https://mlsanity.com/paper/2502.04558/) (2025)
- [Understanding the Anchoring Effect of LLM with Synthetic Data: Existence, Mechanism, and Potential Mitigations](https://mlsanity.com/paper/2505.15392/) (2025)
- [NL2GenSym: Natural Language to Generative Symbolic Rules for SOAR Cognitive Architecture via Large Language Models](https://mlsanity.com/paper/2510.09355/) (2025)
- [Belief-Aware VLM Model for Human-like Reasoning](https://mlsanity.com/paper/2604.09686/) (2026)
- [Toward Human-Centered Multi-Agent Systems: Integrating Cognition, Culture, Values, and Cooperation in AI Agents](https://mlsanity.com/paper/2606.08274/) (2026)

## Abstract (arXiv)

Resolving the dichotomy between the human-like yet constrained reasoning processes of Cognitive Architectures and the broad but often noisy inference behavior of Large Language Models (LLMs) remains a challenging but exciting pursuit, for enabling reliable machine reasoning capabilities in production systems. Because Cognitive Architectures are famously developed for the purpose of modeling the internal mechanisms of human cognitive decision-making at a computational level, new investigations consider the goal of informing LLMs with the knowledge necessary for replicating such processes, e.g., guided perception, memory, goal-setting, and action. Previous approaches that use LLMs for grounded decision-making struggle with complex reasoning tasks that require slower, deliberate cognition over fast and intuitive inference -- reporting issues related to the lack of sufficient grounding, as in hallucination. To resolve these challenges, we introduce LLM-ACTR, a novel neuro-symbolic architecture that provides human-aligned and versatile decision-making by integrating the ACT-R Cognitive Architecture with LLMs. Our framework extracts and embeds knowledge of ACT-R's internal decision-making process as latent neural representations, injects this information into trainable LLM adapter layers, and fine-tunes the LLMs for downstream prediction. Our experiments on novel Design for Manufacturing tasks show both improved task performance as well as improved grounded decision-making capability of our approach, compared to LLM-only baselines that leverage chain-of-thought reasoning strategies.