@article{reinforcementlearninginhyperbolicspacefo,
  title = {Reinforcement Learning in hyperbolic space for multi-step reasoning},
  author = {Tao Xu and Dung-Yang Lee and Momiao Xiong},
  year = {2025},
  eprint = {2507.16864},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2507.16864},
}