@article{octothinkermidtrainingincentivizes,
  title = {OctoThinker: Mid-training Incentivizes Reinforcement Learning Scaling},
  author = {Zengzhi Wang and Fan Zhou and Xuefeng Li and PengFei Liu},
  year = {2025},
  eprint = {2506.20512},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2506.20512v1},
}