# An Analysis and Comparison of ACT-R and Soar

arXiv: https://arxiv.org/abs/2201.09305 · HTML: https://mlsanity.com/paper/2201.09305/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 0 of its 27 references that are in the map.
- First posted on arXiv 23 Jan 2022.

## Built on by (most cited first, 12 of 12)

- [Attention Heads of Large Language Models: A Survey](https://mlsanity.com/paper/2409.03752/) (2024)
- [Agentic AI: A Comprehensive Survey of Architectures, Applications, and Future Directions](https://mlsanity.com/paper/2510.25445/) (2025)
- [Towards Autonomous Testing Agents via Conversational Large Language Models](https://mlsanity.com/paper/2306.05152/) (2023)
- [Agentic Visualization: Extracting Agent-based Design Patterns from Visualization Systems](https://mlsanity.com/paper/2505.19101/) (2025)
- [Agents Are Not Enough](https://mlsanity.com/paper/2412.16241/) (2024)
- [Games Agents Play: Towards Transactional Analysis in LLM-based Multi-Agent Systems](https://mlsanity.com/paper/2507.21354/) (2025)
- [NL2GenSym: Natural Language to Generative Symbolic Rules for SOAR Cognitive Architecture via Large Language Models](https://mlsanity.com/paper/2510.09355/) (2025)
- [Introduction to Soar](https://mlsanity.com/paper/2205.03854/) (2022)
- [Towards Neural Network based Cognitive Models of Dynamic Decision-Making by Humans](https://mlsanity.com/paper/2407.17622/) (2024)
- [Decision-Making Amid Information-Based Threats in Sociotechnical Systems: A Review](https://mlsanity.com/paper/2511.11595/) (2025)
- [The Observer-Situation Lattice: A Unified Formal Basis for Perspective-Aware Cognition](https://mlsanity.com/paper/2603.01407/) (2026)
- [CEAA: A Cognitive Embodied Agents Architecture for Interactive Computing Systems](https://mlsanity.com/paper/2608.09848/) (2026)

## Abstract (arXiv)

This is a detailed analysis and comparison of the ACT-R and Soar cognitive architectures, including their overall structure, their representations of agent data and metadata, and their associated processing. It focuses on working memory, procedural memory, and long-term declarative memory. I emphasize the commonalities, which are many, but also highlight the differences. I identify the processes and distinct classes of information used by these architectures, including agent data, metadata, and meta-process data, and explore the roles that metadata play in decision making, memory retrievals, and learning.