@article{wildrewardlearningrewardmodelsfrominthew,
  title = {WildReward: Learning Reward Models from In-the-Wild Human Interactions},
  author = {Hao Peng and Yunjia Qi and Xiaozhi Wang and Zijun Yao and Lei Hou and Juanzi Li},
  year = {2026},
  eprint = {2602.08829},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2602.08829},
}