@article{rethinkingcriticlearninginppounderstandi, title = {Rethinking Critic Learning in PPO: Understanding 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}, year = {2026}, eprint = {2609.18708}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.18708}, }