---
title: "SOAR: An architecture for general intelligence (1987)"
description: "Soar addresses a central goal of AI: a single fixed architecture that can handle the full range of… 18 references, cited by 21 papers here."
authors: ["John E. Laird", "Allen Newell", "Paul S. Rosenbloom"]
year: 1987
venue: "Artificial Intelligence"
source: "http://iiif.library.cmu.edu/file/Newell_box00011_fld00804_doc0002/Newell_box00011_fld00804_doc0002.pdf"
licence: "All rights reserved — free to read at the source"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/laird-1987-soar-architecture-general-intelligence/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/laird-1987-soar-architecture-general-intelligence/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [1987](https://md.research.elamur.ai/free/en/papers/1987/) / SOAR: An architecture for general intelligence

# SOAR: An architecture for general intelligence

**Authors:** John E. Laird, Allen Newell and Paul S. Rosenbloom · **Year:** 1987 · **Venue:** [Artificial Intelligence](https://md.research.elamur.ai/free/en/venues/artificial-intelligence/) ([Artificial Intelligence 1987](https://md.research.elamur.ai/free/en/venues/artificial-intelligence/1987/)) · **Publisher:** [Elsevier BV](https://md.research.elamur.ai/free/en/publishers/elsevier-bv/) · **Licence:** All rights reserved — free to read at the source

**Links:** [PDF](http://iiif.library.cmu.edu/file/Newell_box00011_fld00804_doc0002/Newell_box00011_fld00804_doc0002.pdf) · [OpenAlex](https://openalex.org/W2180809782)

**Citations:** 2,419 citations (OpenAlex, 2026-10-14) · [21](https://md.research.elamur.ai/free/en/papers/laird-1987-soar-architecture-general-intelligence/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
Soar addresses a central goal of AI: a single fixed architecture that can handle the full range of cognitive tasks, from routine to hard problems, and that improves with experience. Laird, Newell and Rosenbloom cast all goal-directed behaviour as search in problem spaces. Knowledge is stored as productions in long-term memory and matched against a shared working memory. Each decision cycle has two parts: an elaboration phase that fires every matching production in parallel, and a fixed decision procedure that weighs preferences to select problem spaces, states and operators. When knowledge is missing or conflicting, Soar reaches an impasse and automatically creates a subgoal to resolve it (universal subgoaling). Chunking stores the results of these subgoals as new productions, so learning comes from the same mechanism as problem solving. The authors show the system on classic puzzles, weak search methods and knowledge-intensive expert tasks. The work matters because it was one of the first unified cognitive architectures, and it shaped later research on cognitive modelling and integrated agents.

## Key points
- **Architecture:** problem spaces, a production-based long-term memory and a working memory. A decision cycle alternates elaboration with preference-based selection of spaces, states and operators.
- **Impasses:** ties, conflicts, no-change and rejection automatically trigger subgoals. This lets the architecture generate its own goal hierarchy.
- **Weak methods:** general methods such as hill climbing, means-ends analysis and lookahead arise from task knowledge rather than separate code (the "universal weak method").
- **Chunking:** this is the only learning mechanism. It turns subgoal results into productions, which speeds up later performance and transfers within and across tasks.
- **Demonstrations:** tasks include the Eight Puzzle and Tower of Hanoi, plus expert-system work such as R1-Soar for VAX configuration.
- **Source note:** the extracted text supplied here contained only the title page (dated draft January 1986) and funding notes. This summary therefore reflects the paper's widely known published content, not the provided extract.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [Stanford University](https://md.research.elamur.ai/free/en/universities/stanford-university/) — University, Stanford, United States · 434 works · 314,419 citations
- [Carnegie Mellon University](https://md.research.elamur.ai/free/en/universities/carnegie-mellon-university/) — University, Pittsburgh, United States · 539 works · 179,533 citations
- [Palo Alto Research Center](https://md.research.elamur.ai/free/en/labs/palo-alto-research-center/) — Research institute, Palo Alto, United States · 14 works · 8,123 citations

📚 Shelves (2): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works

💡 Concepts (1): [💡 Artificial intelligence](https://md.research.elamur.ai/free/en/concepts/artificial-intelligence/) · 49 works

## Cite

Cite as: John E. Laird, Allen Newell and Paul S. Rosenbloom. 1987. SOAR: An architecture for general intelligence. Artificial Intelligence.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{laird1987soar,
  title = {{SOAR: An architecture for general intelligence}},
  author = {John E. Laird, Allen Newell and Paul S. Rosenbloom},
  booktitle = {Artificial Intelligence},
  year = {1987},
  doi = {10.1016/0004-3702(87)90050-6},
  url = {https://doi.org/10.1016/0004-3702(87)90050-6}
}
```

- [← previous Politeness: Some Universals in Language Usage](https://md.research.elamur.ai/free/en/papers/brown-1987-politeness-some-universals-language-usage/)
- [next → A Centering Approach to Pronouns](https://md.research.elamur.ai/free/en/papers/brennan-1987-centering-approach-pronouns/)
- [↑ back to papers of 1987](https://md.research.elamur.ai/free/en/papers/1987/)

## References

18 references, 0 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Rosenbloom, P. S. The Chunking of Goal Hierarchies: A model of practice and stimulus-response compatibility. Doctoral dissertation, Camegie-Mellon University, 1983, (available as Tech Rep \#83-148, Computer Science Department). [find](https://scholar.google.com/scholar?q=Rosenbloom%2C+P%2E+S%2E+The+Chunking+of+Goal+Hierarchies%3A+A+model+of+practice+and+stimulus%2Dresponse+compatibility%2E+Doctoral+dissertation%2C+Camegie%2DMellon+University%2C+1983%2C+%28available+as+Tech+Rep+%5C%2383%2D148%2C+Co)
2. Rosenbloom, P. & Newell, A. The chunking of goal hierarchies: A generalized model of practice. In Michalski, R. S. (Ed.), Proceedings of the International Machine Learning Workshop. Urbana-Champaign, IL: Department of Computer Science, University of Illinois, 1983. . [find](https://scholar.google.com/scholar?q=Rosenbloom%2C+P%2E+%26+Newell%2C+A%2E+The+chunking+of+goal+hierarchies%3A+A+generalized+model+of+practice%2E+In+Michalski%2C+R%2E+S%2E+%28Ed%2E%29%2C+Proceedings+of+the+International+Machine+Learning+Workshop%2E+Urbana%2DChampaign%2C+)
3. Rosenbloom, P. S., & Newell, A. The chunking of goal hierarchies: A generalized model of practice. In R. S. Michalski, J. G. Carbonell, & T. M. Mitchell (Eds.), Machine Learning: An Artificial Intelligence Approach, Volume II. Los Altos, CA: Morgan Kaufmann Publishers, Inc., 1985. In press (Also ava… [find](https://scholar.google.com/scholar?q=Rosenbloom%2C+P%2E+S%2E%2C+%26+Newell%2C+A%2E+The+chunking+of+goal+hierarchies%3A+A+generalized+model+of+practice%2E+In+R%2E+S%2E+Michalski%2C+J%2E+G%2E+Carbonell%2C+%26+T%2E+M%2E+Mitchell+%28Eds%2E%29%2C+Machine+Learning%3A+An+Artificial+Intelli)
4. Rosenbloom, P. S., Laird, J. E., McDermott, J., Newell, A., £ Orciuch, E. Rl-Soar: An experiment in knowledge-intensive programming in a problem-solving architecture. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1985, 7(5), 561-569. (Also available in Proceedings of the IEEE Works… [find](https://scholar.google.com/scholar?q=Rosenbloom%2C+P%2E+S%2E%2C+Laird%2C+J%2E+E%2E%2C+McDermott%2C+J%2E%2C+Newell%2C+A%2E%2C+%C2%A3+Orciuch%2C+E%2E+Rl%2DSoar%3A+An+experiment+in+knowledge%2Dintensive+programming+in+a+problem%2Dsolving+architecture%2E+IEEE+Transactions+on+Pattern+Anal)
5. Rychener, M. D. Production systems as a programming langaugefor artificial intelligence applications (Tech. Rep.). Computer Science Department, Carnegie-Mellon University, 1976. [find](https://scholar.google.com/scholar?q=Rychener%2C+M%2E+D%2E+Production+systems+as+a+programming+langaugefor+artificial+intelligence+applications+%28Tech%2E+Rep%2E%29%2E+Computer+Science+Department%2C+Carnegie%2DMellon+University%2C+1976%2E)
6. Rychener, M. D. The instructable production system: A retrospective analysis. In Michalski, R. S., Carbonell, J. G. & Mitchell, T. M. (Eds.), Machine Learning: An artificial intelligence approach. Palo Alto, CA: Tioga, 1983. [find](https://scholar.google.com/scholar?q=Rychener%2C+M%2E+D%2E+The+instructable+production+system%3A+A+retrospective+analysis%2E+In+Michalski%2C+R%2E+S%2E%2C+Carbonell%2C+J%2E+G%2E+%26+Mitchell%2C+T%2E+M%2E+%28Eds%2E%29%2C+Machine+Learning%3A+An+artificial+intelligence+approach%2E+Pal)
7. Rychener, M. D. & Newell, A. An instructable production system: Basic design issues. In Waterman, D. A. & Hayes-Roth, F. (Eds.), Pattern-Directed Inference Systems. New York: Academic Press, 1978. [find](https://scholar.google.com/scholar?q=Rychener%2C+M%2E+D%2E+%26+Newell%2C+A%2E+An+instructable+production+system%3A+Basic+design+issues%2E+In+Waterman%2C+D%2E+A%2E+%26+Hayes%2DRoth%2C+F%2E+%28Eds%2E%29%2C+Pattern%2DDirected+Inference+Systems%2E+New+York%3A+Academic+Press%2C+1978%2E)
8. Sacerdoti, E. D. The nonlinear nature of plans. In Proceedings of the International Joint Conference on Artificial Intelligence. IJCAI, 1975. [find](https://scholar.google.com/scholar?q=Sacerdoti%2C+E%2E+D%2E+The+nonlinear+nature+of+plans%2E+In+Proceedings+of+the+International+Joint+Conference+on+Artificial+Intelligence%2E+IJCAI%2C+1975%2E)
9. Sacerdoti, E. D. A Stmcturefor Plans and Behavior. New York: Elsevier, 1977. [find](https://scholar.google.com/scholar?q=Sacerdoti%2C+E%2E+D%2E+A+Stmcturefor+Plans+and+Behavior%2E+New+York%3A+Elsevier%2C+1977%2E)
10. Shortliffe, E. H. Computer-based Medical Consultations: MYCIN. New York: American Elsevier, 1976. [find](https://scholar.google.com/scholar?q=Shortliffe%2C+E%2E+H%2E+Computer%2Dbased+Medical+Consultations%3A+MYCIN%2E+New+York%3A+American+Elsevier%2C+1976%2E)
11. Simon, H. A. Search and reasoning in problem solving. Artificial Intelligence, 1983, 21, 7-30. van de Drug, A., Rosenbloom, P. S., & Newell, A. Some Experiments with Rl-Soar (Tech. Rep.). [find](https://scholar.google.com/scholar?q=Simon%2C+H%2E+A%2E+Search+and+reasoning+in+problem+solving%2E+Artificial+Intelligence%2C+1983%2C+21%2C+7%2D30%2E+van+de+Drug%2C+A%2E%2C+Rosenbloom%2C+P%2E+S%2E%2C+%26+Newell%2C+A%2E+Some+Experiments+with+Rl%2DSoar+%28Tech%2E+Rep%2E%29%2E)
12. Computer Science Department, Carnegie-Mellon University, 1986. (in preparation). [find](https://scholar.google.com/scholar?q=Computer+Science+Department%2C+Carnegie%2DMellon+University%2C+1986%2E+%28in+preparation%29%2E)
13. VanLehn, K. Felicity Conditions for Human Skill Acquisition: Validating an A I-Based Theory (Tech. Rep.). Xerox Palo Alto Reserch Center, November 1983. [find](https://scholar.google.com/scholar?q=VanLehn%2C+K%2E+Felicity+Conditions+for+Human+Skill+Acquisition%3A+Validating+an+A+I%2DBased+Theory+%28Tech%2E+Rep%2E%29%2E+Xerox+Palo+Alto+Reserch+Center%2C+November+1983%2E)
14. Waltz, D. L. Understanding line drawings of scenes with shadows. In Winston, P. H. (Ed.), The Pyschology of Computer Vision. New York: McGraw-Hill, 1975. [find](https://scholar.google.com/scholar?q=Waltz%2C+D%2E+L%2E+Understanding+line+drawings+of+scenes+with+shadows%2E+In+Winston%2C+P%2E+H%2E+%28Ed%2E%29%2C+The+Pyschology+of+Computer+Vision%2E+New+York%3A+McGraw%2DHill%2C+1975%2E)
15. Waterman, D. A. & Hayes-Roth, F., (Eds.). Press, 1978. [find](https://scholar.google.com/scholar?q=Waterman%2C+D%2E+A%2E+%26+Hayes%2DRoth%2C+F%2E%2C+%28Eds%2E%29%2E+Press%2C+1978%2E)
16. Wilensky, R. Planning and Understanding: A computational approach to human reasoning. Reading, MA: Addison-Wesley, 1983. [find](https://scholar.google.com/scholar?q=Wilensky%2C+R%2E+Planning+and+Understanding%3A+A+computational+approach+to+human+reasoning%2E+Reading%2C+MA%3A+Addison%2DWesley%2C+1983%2E)
17. Winston, P. Artificial Intelligence, 2nd cd.. Reading, MA: Addison-Wesley, 1984. [find](https://scholar.google.com/scholar?q=Winston%2C+P%2E+Artificial+Intelligence%2C+2nd+cd%2E%2E+Reading%2C+MA%3A+Addison%2DWesley%2C+1984%2E)
18. PAGE 59 Pattern Directed Inference Systems. New York: Academic [find](https://scholar.google.com/scholar?q=PAGE+59+Pattern+Directed+Inference+Systems%2E+New+York%3A+Academic)

*Updated 29 October 2026*