@article{efficientrltrainingforreasoningmodels,
  title = {Efficient RL Training for Reasoning Models via Length-Aware Optimization},
  author = {Danlong Yuan and Tian Xie and Shaohan Huang and Zhuocheng Gong and Huishuai Zhang and Chong Luo and Furu Wei and Dongyan Zhao},
  year = {2025},
  eprint = {2505.12284},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2505.12284v1},
}