@article{beyondthetradeoffselfsupervisedreinforce,
  title = {Beyond the Trade-off: Self-Supervised Reinforcement Learning for Reasoning Models' Instruction Following},
  author = {Qingyu Ren and Qianyu He and Bowei Zhang and Jie Zeng and Jiaqing Liang and Yanghua Xiao and Weikang Zhou and Zeye Sun and Fei Yu},
  year = {2025},
  eprint = {2508.02150},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2508.02150},
}