Document Open Access Logo

Balancing Latin Rectangles with LLM-Generated Streamliners

Authors Florentina Voboril , Vaidyanathan Peruvemba Ramaswamy , Stefan Szeider

PDF HTML 5

Files

Thumbnail PDF
PDF
LIPIcs.CP.2025.36.pdf
  • Filesize: 0.86 MB
  • 17 pages
HTML5 Logo HTML (experimental)
LIPIcs.CP.2025.36.html

Document Identifiers

Subject Classification

ACM Subject Classification
  • Theory of computation → Constraint and logic programming
  • Mathematics of computing → Combinatorial optimization
  • Mathematics of computing → Combinatorial algorithms
  • Information systems → Language models
Keywords
  • Balanced Latin Rectangles
  • Streamliners
  • Large Language Models
  • Warmstarts
  • Evolutionary Search

Metrics

  • Access Statistics
  • Total Accesses (updated on a weekly basis)
    0
    PDF Downloads
    0
    Metadata Views

Abstract

We present an integration of Large Language Models (LLMs) with streamlining techniques to find well-balanced Latin rectangles. Our approach combines LLM-generated streamlining constraints that effectively partition the search space, directing constraint solvers toward structured subspaces containing high-quality solutions. Our methodology extends LLM-generated streamliners, as Voboril et al. (2024) introduced for decision problems, to the optimization context through techniques that incrementally refine the objective function value.
We propose two complementary strategies to orchestrate sets of streamliners: an incremental mechanism that utilizes improving solutions to initialize subsequent search processes, and an evolutionary framework that maintains and refines effective streamliner populations. Our experiments demonstrate that our approach successfully reduces established minimum imbalance values for partially spatially balanced Latin rectangles across multiple problem dimensions. The results validate the efficacy of combining LLMs with constraint programming methodologies for tackling problems characterized by complex global constraints.

Cite As Get BibTex

Florentina Voboril, Vaidyanathan Peruvemba Ramaswamy, and Stefan Szeider. Balancing Latin Rectangles with LLM-Generated Streamliners. In 31st International Conference on Principles and Practice of Constraint Programming (CP 2025). Leibniz International Proceedings in Informatics (LIPIcs), Volume 340, pp. 36:1-36:17, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2025) https://doi.org/10.4230/LIPIcs.CP.2025.36

Author Details

Florentina Voboril
  • Algorithms and Complexity Group, TU Wien, Austria
Vaidyanathan Peruvemba Ramaswamy
  • Algorithms and Complexity Group, TU Wien, Austria
Stefan Szeider
  • Algorithms and Complexity Group, TU Wien, Austria

Funding

Austrian Science Fund (FWF) projects 10.55776/COE12 and 10.55776/P36420.

Supplementary Materials

References

  1. Md. Masbaul Alam, M. A. Hakim Newton, and Abdul Sattar. Constraint-based search for optimal Golomb rulers. J. Heuristics, 23(6):501-532, 2017. URL: https://doi.org/10.1007/s10732-017-9353-x.
  2. Mateo Díaz, Ronan Le Bras, and Carla P. Gomes. In search of balance: The challenge of generating balanced Latin rectangles. In Domenico Salvagnin and Michele Lombardi, editors, Integration of AI and OR Techniques in Constraint Programming - 14th International Conference, CPAIOR 2017, Padua, Italy, June 5-8, 2017, Proceedings, volume 10335 of Lecture Notes in Computer Science, pages 68-76. Springer, 2017. URL: https://doi.org/10.1007/978-3-319-59776-8_6.
  3. Carla P. Gomes and Meinolf Sellmann. Streamlined constraint reasoning. In Mark Wallace, editor, Principles and Practice of Constraint Programming - CP 2004, 10th International Conference, CP 2004, Toronto, Canada, September 27 - October 1, 2004, Proceedings, volume 3258 of Lecture Notes in Computer Science, pages 274-289. Springer, 2004. URL: https://doi.org/10.1007/978-3-540-30201-8_22.
  4. Aditya Grover, Tudor Achim, and Stefano Ermon. Streamlining variational inference for constraint satisfaction problems. In Samy Bengio, Hanna M. Wallach, Hugo Larochelle, Kristen Grauman, Nicolò Cesa-Bianchi, and Roman Garnett, editors, Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, NeurIPS 2018, December 3-8, 2018, Montréal, Canada, pages 10579-10589, 2018. URL: https://proceedings.neurips.cc/paper/2018/hash/02ed812220b0705fabb868ddbf17ea20-Abstract.html.
  5. Marijn J. H. Heule, Manuel Kauers, and Martina Seidl. Local search for fast matrix multiplication. In Mikolás Janota and Inês Lynce, editors, Theory and Applications of Satisfiability Testing - SAT 2019 - 22nd International Conference, SAT 2019, Lisbon, Portugal, July 9-12, 2019, Proceedings, volume 11628 of Lecture Notes in Computer Science, pages 155-163. Springer, 2019. URL: https://doi.org/10.1007/978-3-030-24258-9_10.
  6. Marcus Jones, Richard Woodward, and Jerry Stoller. Increasing precision in agronomic field trials using Latin square designs. Agronomy Journal, 107(1):20-24, 2015. URL: https://doi.org/10.2134/agronj14.0232.
  7. Ronan LeBras, Carla P. Gomes, and Bart Selman. From streamlined combinatorial search to efficient constructive procedures. In Jörg Hoffmann and Bart Selman, editors, Proceedings of the Twenty-Sixth AAAI Conference on Artificial Intelligence, July 22-26, 2012, Toronto, Ontario, Canada, pages 499-506. AAAI Press, 2012. URL: https://doi.org/10.1609/aaai.v26i1.8147.
  8. Zhenjun Liu, Leroy Chew, and Marijn J. H. Heule. Avoiding monochromatic rectangles using shift patterns. In Hang Ma and Ivan Serina, editors, Proceedings of the Fourteenth International Symposium on Combinatorial Search, SOCS 2021, Virtual Conference [Jinan, China], July 26-30, 2021, pages 225-227. AAAI Press, 2021. URL: https://doi.org/10.1609/socs.v12i1.18591.
  9. Renee Mirka, Laura Greenstreet, Marc Grimson, and Carla P. Gomes. A new approach to finding 2 x n partially spatially balanced Latin rectangles (short paper). In Roland H. C. Yap, editor, 29th International Conference on Principles and Practice of Constraint Programming, CP 2023, August 27-31, 2023, Toronto, Canada, volume 280 of LIPIcs, pages 47:1-47:11. Schloss Dagstuhl - Leibniz-Zentrum für Informatik, 2023. URL: https://doi.org/10.4230/LIPIcs.CP.2023.47.
  10. Vaidyanathan Peruvemba Ramaswamy and Stefan Szeider. Proven optimally-balanced Latin rectangles with SAT (short paper). In Roland H. C. Yap, editor, 29th International Conference on Principles and Practice of Constraint Programming, CP 2023, August 27-31, 2023, Toronto, Canada, volume 280 of LIPIcs, pages 48:1-48:10. Schloss Dagstuhl - Leibniz-Zentrum für Informatik, 2023. URL: https://doi.org/10.4230/LIPIcs.CP.2023.48.
  11. Casey Smith, Carla P. Gomes, and Cèsar Fernández. Streamlining local search for spatially balanced Latin squares. In Leslie Pack Kaelbling and Alessandro Saffiotti, editors, IJCAI-05, Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence, Edinburgh, Scotland, UK, July 30 - August 5, 2005, pages 1539-1540. Professional Book Center, 2005. URL: http://ijcai.org/Proceedings/05/Papers/post-0460.pdf.
  12. Patrick Spracklen, Özgür Akgün, and Ian Miguel. Automatic generation and selection of streamlined constraint models via Monte Carlo search on a model lattice. In John N. Hooker, editor, Principles and Practice of Constraint Programming - 24th International Conference, CP 2018, Lille, France, August 27-31, 2018, Proceedings, volume 11008 of Lecture Notes in Computer Science, pages 362-372. Springer, 2018. URL: https://doi.org/10.1007/978-3-319-98334-9_24.
  13. Patrick Spracklen, Nguyen Dang, Özgür Akgün, and Ian Miguel. Automatic streamlining for constrained optimisation. In Thomas Schiex and Simon de Givry, editors, Principles and Practice of Constraint Programming - 25th International Conference, CP 2019, Stamford, CT, USA, September 30 - October 4, 2019, Proceedings, volume 11802 of Lecture Notes in Computer Science, pages 366-383. Springer, 2019. URL: https://doi.org/10.1007/978-3-030-30048-7_22.
  14. Patrick Spracklen, Nguyen Dang, Özgür Akgün, and Ian Miguel. Towards portfolios of streamlined constraint models: A case study with the Balanced Academic Curriculum Problem. CoRR, abs/2009.10152, 2020. URL: https://doi.org/10.48550/arXiv.2009.10152.
  15. Patrick Spracklen, Nguyen Dang, Özgür Akgün, and Ian Miguel. Automated streamliner portfolios for constraint satisfaction problems. Artificial Intelligence, 319:103915, 2023. URL: https://doi.org/10.1016/J.ARTINT.2023.103915.
  16. Nseobong Peter Uto and RA Bailey. Balanced semi-Latin rectangles: properties, existence and constructions for block size two. Journal of Statistical Theory and Practice, 14(3):51, 2020. Google Scholar
  17. H.M. van Es and C.L. van Es. Spatial nature of randomization and its effect on the outcome of field experiments. Agronomy Journal, 85(2):420-428, 1993. Google Scholar
  18. Florentina Voboril, Vaidyanathan Peruvemba Ramaswamy, and Stefan Szeider. StreamLLM: Enhancing constraint programming with large language model-generated streamliners. In 2025 IEEE/ACM 1st International Workshop on Neuro-Symbolic Software Engineering (NSE), pages 17-22, Los Alamitos, CA, USA, May 2025. IEEE Computer Soc. URL: https://doi.ieeecomputersociety.org/10.1109/NSE66660.2025.00010, URL: https://doi.org/10.1109/NSE66660.2025.00010.
  19. Florentina Voboril, Vaidyanathan Peruvemba Ramaswamy, and Stefan Szeider. Supplementary material for paper - Balancing Latin Rectangles with LLM-generated Streamliners, June 2025. URL: https://doi.org/10.5281/zenodo.15616074.
  20. James Wetter, Özgür Akgün, and Ian Miguel. Automatically generating streamlined constraint models with Essence and Conjure. In Gilles Pesant, editor, Principles and Practice of Constraint Programming - 21st International Conference, CP 2015, Cork, Ireland, August 31 - September 4, 2015, Proceedings, volume 9255 of Lecture Notes in Computer Science, pages 480-496. Springer, 2015. URL: https://doi.org/10.1007/978-3-319-23219-5_34.
Any Issues?
X

Feedback on the Current Page

CAPTCHA

Thanks for your feedback!

Feedback submitted to Dagstuhl Publishing

Could not send message

Please try again later or send an E-mail
© 2023-2025 Schloss Dagstuhl – LZI GmbH About DROPS Imprint Privacy Contact