@article{ticgrpoprovableandefficientoptimizationf,
  title = {TIC-GRPO: Provable and Efficient Optimization for Reinforcement Learning from Human Feedback},
  author = {Lei Pang and Jun Luo and Ruinan Jin},
  year = {2025},
  eprint = {2508.02833},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2508.02833},
}