@article{sspposemanticcalibratedselfplaypreferenc,
  title = {S-SPPO: Semantic-Calibrated Self-Play Preference Optimization},
  author = {Xiwen Chen and Wenhui Zhu and Jingjing Wang and Peijie Qiu and Zhipeng Wang and Huayu Li and ZhengXiao He and Xuanzhao Dong and Prayag Tiwari and Mingkun Xu and Yujian Xiong and Feng Luo and Abolfazl Razi and Brendan Hogan Rappazzo and Anderson Schneider and Yuriy Nevmyvaka},
  year = {2026},
  eprint = {2606.01561},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.01561},
}