@article{yourrewardfunctionforrlisyourbestprmfors,
  title = {AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning},
  author = {Can Jin and Yang Zhou and Qixin Zhang and Hongwu Peng and Di Zhang and Zihan Dong and Marco Pavone and Ligong Han and Zhang-Wei Hong and Tong Che and Dimitris N. Metaxas},
  year = {2025},
  eprint = {2508.14313},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2508.14313},
}