@inproceedings{zheng-etal-2026-comprehensive,
    title = "A Comprehensive Survey of Process Reward Models: Data Generation, Model Construction, and Usage",
    author = "Zheng, Congmin  and
      Zhu, Jiachen  and
      Ou, Zhuoying  and
      Chen, Yuxiang  and
      Zhang, Kangning  and
      Shan, Rong  and
      Zheng, Zeyu  and
      Yang, Mengyue  and
      Lin, Jianghao  and
      Yu, Yong  and
      Zhang, Weinan",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.163/",
    pages = "3591--3607",
    ISBN = "979-8-89176-390-6",
    abstract = "Large Language Models (LLMs) have advanced reasoning ability, yet conventional alignment remains dominated by outcome reward models (ORMs) that judge only final answers. Process Reward Models(PRMs) address this gap by evaluating and guiding reasoning at the step or trajectory level. This survey provides a systematic overview of PRMs through the full loop: how to generate process data, build PRMs, and use PRMs for test-time scaling and reinforcement learning. We summarize applications across math, code, text, multimodal reasoning, robotics, and agents, and review emerging benchmarks. Our goal is to clarify design spaces, reveal open challenges, and guide future research toward fine-grained, robust reasoning alignment."
}