@article{alleviatingsparserewardsbymodelingstepwi,
  title = {Alleviating Sparse Rewards by Modeling Step-Wise and Long-Term Sampling Effects in Flow-Based GRPO},
  author = {Yunze Tong and Mushui Liu and Canyu Zhao and Didi Zhu and Wanggui He and Shiyi Zhang and Hongwei Zhang and Peng Zhang and Jinlong Liu and Hao Jiang},
  year = {2026},
  eprint = {2602.06422},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2602.06422},
}