@article{commonbenchmarksundervaluethe,
  title = {Common Benchmarks Undervalue the Generalization Power of Programmatic Policies},
  author = {Amirhossein Rajabpour and Kiarash Aghakasiri and Sandra Zilles and Levi H. S. Lelis},
  year = {2025},
  eprint = {2506.14162},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2506.14162v1},
}