@article{l1controllinghowlongareasoningmodel,
  title = {L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning},
  author = {Pranjal Aggarwal and Sean Welleck},
  year = {2025},
  eprint = {2503.04697},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2503.04697v1},
}