@article{gupogradientuncertaintyawarepolicyoptimi,
  title = {GUPO: Gradient Uncertainty-aware Policy Optimization for Post-Training Large Language Models},
  author = {Peizheng Guo and Jianqi Zhang and Xingyu Zhang and Yun Fan and Jiahuan Zhou and Changwen Zheng and Wenwen Qiang},
  year = {2026},
  eprint = {2608.17411},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2608.17411},
}