@article{prorlprolongedreinforcementlearning,
  title = {ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models},
  author = {Mingjie Liu and Shizhe Diao and Ximing Lu and Jian Hu and Xin Dong and Yejin Choi and Jan Kautz and Yi Dong},
  year = {2025},
  eprint = {2505.24864},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2505.24864v1},
}