@article{ghpoadaptiveguidanceforstableandefficien,
  title = {GHPO: Adaptive Guidance for Stable and Efficient LLM Reinforcement Learning},
  author = {Ziru Liu and Cheng Gong and Xinyu Fu and Yaofang Liu and Ran Chen and Shoubo Hu and Suiyun Zhang and Rui Liu and Qingfu Zhang and Dandan Tu},
  year = {2025},
  eprint = {2507.10628},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2507.10628},
}