@article{learntoreasonefficientlywithadaptive,
  title = {Learn to Reason Efficiently with Adaptive Length-based Reward Shaping},
  author = {Wei Liu and Ruochen Zhou and Yiyun Deng and Yuzhen Huang and Junteng Liu and Yuntian Deng and Yizhe Zhang and Junxian He},
  year = {2025},
  eprint = {2505.15612},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2505.15612v1},
}