@article{s2rteachingllmstoselfverifyandself,
  title = {S$^2$R: Teaching LLMs to Self-verify and Self-correct via Reinforcement Learning},
  author = {Ruotian Ma and Peisong Wang and Cheng Liu and Xingyan Liu and Jiaqi Chen and Bang Zhang and Xin Zhou and Nan Du and Jia Li},
  year = {2025},
  eprint = {2502.12853},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2502.12853v1},
}