@article{grad2rewardfromsparsejudgmenttodenserewa,
  title = {Grad2Reward: From Sparse Judgment to Dense Rewards for Improving Open-Ended LLM Reasoning},
  author = {Zheng Zhang and Ao Lu and Yuanhao Zeng and Ziwei Shan and Jinjin Guo and Lufei Li and Yexin Li and Kan Ren},
  year = {2026},
  eprint = {2602.01791},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2602.01791},
}