@article{oblrpoatheoreticalframeworkforstablerein,
  title = {Variance-Aware Baselines and Adaptive Learning Rates for Reinforcement Learning with Verifiable Rewards},
  author = {Zixun Huang and Jiayi Sheng and Zeyu Zheng},
  year = {2025},
  eprint = {2511.23310},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2511.23310},
}