@article{fp8rlapracticalandstablelowprecisionstac,
  title = {FP8-RL: A Practical and Stable Low-Precision Stack for LLM Reinforcement Learning},
  author = {Zhaopeng Qiu and Shuang Yu and Jingqi Zhang and Shuai Zhang and Xue Huang and Jingyi Yang and Junjie Lai},
  year = {2026},
  eprint = {2601.18150},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2601.18150},
}