@article{quantileadvantageestimationstabilizingrl,
  title = {Quantile Advantage Estimation: Stabilizing RLVR for LLM Reasoning},
  author = {Junkang Wu and Kexin Huang and Jiancan Wu and An Zhang and Xiang Wang and Xiangnan He},
  year = {2025},
  eprint = {2509.22611},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2509.22611},
}