@article{h1bootstrappingllmstoreasonoverlongerhor,
  title = {h1: Bootstrapping LLMs to Reason over Longer Horizons via Reinforcement Learning},
  author = {Sumeet Ramesh Motwani and Alesia Ivanova and Ziyang Cai and Philip Torr and Riashat Islam and Shital Shah and Christian Schroeder de Witt and Charles London},
  year = {2025},
  eprint = {2510.07312},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2510.07312},
}