Citations

Citing this project

FormulationBench was introduced by FLARE: Verifying MILP Reformulations with LLM-Based Theorem Proving. If you use the dataset or the formulation-bench package, please cite:

@misc{robbins2026flare,
  title={{{FLARE}}: Verifying {{MILP}} Reformulations with {{LLM}}-Based Theorem Proving},
  author={Henry Robbins and Connor Lawless and Madeleine Udell and Ellen Vitercik},
  year={2026},
  eprint={2608.25220},
  archivePrefix={arXiv},
  primaryClass={cs.AI},
  url={https://arxiv.org/abs/2608.25220},
}

References

[1]

Nathan Ferchtandiker, Dick den Hertog, Madeleine Udell, and Segev Wasserkrug. Finding efficient MILO formulations with LLMs. Working paper, 2025. URL: https://github.com/nathan-ferchtandiker/LLMs-For-Optimization-Reformulations.

[2]

Milad Yazdani, Mahdi Mostajabdaveh, Samin Aref, and Zirui Zhou. EvoCut: strengthening integer programs via evolution-guided language models. arXiv preprint arXiv:2508.11850, 2025. URL: https://arxiv.org/abs/2508.11850.

[3]

Haotian Zhai, Connor Lawless, Ellen Vitercik, and Liu Leqi. EquivaMap: leveraging LLMs for automatic equivalence checking of optimization formulations. In Forty-second International Conference on Machine Learning. 2025. URL: https://huggingface.co/datasets/humainlab/EquivaFormulation.