EUVIMEDEUVIMED entdecken
Crossref

Generating Streamlining Constraints with Large Language Models (Abstract Reprint)

Florentina Voboril, Vaidyanathan Peruvemba Ramaswamy, Stefan Szeider

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (47) · 39900-39900

DOI: 10.1609/aaai.v40i47.41415 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Florentina Voboril und 2 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Streamlining constraints (or streamliners, for short) narrow the search space, enhancing the speed and feasibility of solving complex constraint satisfaction problems. Traditionally, streamliners were crafted manually or generated through systematically combined atomic constraints with high-effort offline testing. Our approach utilizes the generative capabilities of Large Language Models (LLMs) to propose effective streamliners for problems specified in the MiniZinc constraint programming language and integrates feedback to the LLM with quick empirical tests for validation. Evaluated across seven diverse constraint satisfaction problems, our method achieves substantial runtime reductions. We compare the results to obfuscated and disguised variants of the problem to see whether the results depend on LLM memorization. We also analyze whether longer offline runs improve the quality of streamliners and whether the LLM can propose good combinations of streamliners.

Zitieren

APA

Voboril, F., Ramaswamy, V. P., & Szeider, S. (2026). Generating Streamlining Constraints with Large Language Models (Abstract Reprint). Proceedings of the AAAI Conference on Artificial Intelligence, 40(47), 39900-39900. https://doi.org/10.1609/aaai.v40i47.41415

Vancouver

Voboril F, Ramaswamy VP, Szeider S. Generating Streamlining Constraints with Large Language Models (Abstract Reprint). Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(47):39900-39900. doi:10.1609/aaai.v40i47.41415

BibTeX
@article{Voboril2026,
  author = {Voboril, Florentina and Ramaswamy, Vaidyanathan Peruvemba and Szeider, Stefan},
  title = {Generating Streamlining Constraints with Large Language Models (Abstract Reprint)},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {47},
  pages = {39900--39900},
  doi = {10.1609/aaai.v40i47.41415}
}
Kostenlos starten →