@article{userlmr1modelinghumanreasoninginuserlang,
  title = {UserLM-R1: Modeling Human Reasoning in User Language Models with Multi-Reward Reinforcement Learning},
  author = {Feng Zhang and Shijia Li and Chunmao Zhang and Zhanyu Ma and Jun Xu and Jiuchong Gao and Jinghua Hao and Renqing He and Jingwen Xu and Han Liu},
  year = {2026},
  eprint = {2601.09215},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2601.09215},
}