@article{rewardrankoptimizingtruelearningtorankut,
  title = {RewardRank: Optimizing True Learning-to-Rank Utility},
  author = {Gaurav Bhatt and Kiran Koshy Thekumparampil and Tanmay Gangwani and Tesi Xiao and Leonid Sigal},
  year = {2025},
  eprint = {2508.14180},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2508.14180},
}