@article{rewardingbetterthinkingforllmpreferencea,
  title = {Rewarding Better Thinking for LLM Preference Alignment},
  author = {Xubo Liu and Wenya Guo and Ruxue Yan and Xinying Qian and Ying Zhang},
  year = {2026},
  eprint = {2607.19824},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2607.19824},
}