@article{li2026rethinking,
  title={Rethinking critic learning in {PPO}: {U}nderstanding and mitigating value flattening},
  author={Yizhuo Li and Jianhao Yan and Yun Luo and Zhi Wang and Futing Wang and Rong-Xi Tan and Kanghui Tian and Ganqu Cui and Ning Ding and Peilin Zhao and Yafu Li and Yu Cheng},
  journal={arXiv:2609.18708},
  year={2026}
}
