@inproceedings{wang-etal-2026-towards,
    title = "Towards Hierarchical Multi-Step Reward Models for Enhanced Reasoning in Large Language Models",
    author = "Wang, Teng  and
      Zhangyi, Jiang  and
      He, Zhenqi  and
      Gong, Hailei  and
      Tong, Shenyang  and
      Yang, Wenhan  and
      Li, Zeyu  and
      Zheng, Yanan  and
      He, Zifan  and
      Ye, Zewen  and
      Ma, Shengjie  and
      Zhang, Jianping",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.27/",
    pages = "565--576",
    ISBN = "979-8-89176-395-1"
}