@article{cvpoenhancingllmreinforcementlearningrea,
  title = {CVPO: Enhancing LLM Reinforcement Learning Reasoning via Value-Variance Adaptation and Dynamic Curriculum Learning},
  author = {Ziqi Jia and Yalu Ouyang and Bo Pang and Panpan Li and Hangfei Xu and Shengzhao Wen and Shiyong Li and Yanpeng Wang},
  year = {2026},
  eprint = {2608.03068},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2608.03068},
}