@article{ulorlanultralongoutputreinforcementlearn,
  title = {UloRL:An Ultra-Long Output Reinforcement Learning Approach for Advancing Large Language Models' Reasoning Abilities},
  author = {Dong Du and Shulin Liu and Tao Yang and Shaohua Chen and Yang Li},
  year = {2025},
  eprint = {2507.19766},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2507.19766},
}