GenPRM: Scaling Test-Time Compute of Process Reward Models via Generative Reasoning

Jian Zhao1,3*, Runze Liu1,2*, Kaiyan Zhang1, Zhimu Zhou3, Junqi Gao4, Dong Li4, Jiafei Lyu1, Zhouyi Qian4, Biqing Qi2†, Xiu Li1†, Bowen Zhou1,2†
1Tsinghua University,
2Shanghai AI Laboratory,
3BUPT,
4Harbin Institute of Technology
*Equal contribution, †Corresponding author
Paper arXiv Code

🤗

 HuggingFace Awesome Process Reward Models

Figure 1: Comparison between GenPRM (right) and previous classification-based PRMs (left).

Figure 2: Overall framework of GenPRM.

Results

BibTeX

@article{zhao2025genprm,
    title   = {GenPRM: Scaling Test-Time Compute of Process Reward Models via Generative Reasoning},
    author  = {Jian Zhao and Runze Liu and Kaiyan Zhang and Zhimu Zhou and Junqi Gao and Dong Li and Jiafei Lyu and Zhouyi Qian and Biqing Qi and Xiu Li and Bowen Zhou},
    journal = {arXiv preprint arXiv:2504.00891},
    year    = {2025}
}
Our collection of PRMs in Awesome-Process-Reward-Models: 
@misc{Awesome-Process-Reward-Models,
    title        = {Awesome Process Reward Models},
    author       = {Runze Liu and Jian Zhao and Kaiyan Zhang and Zhimu Zhou and Junqi Gao and Dong Li and Jiafei Lyu and Zhouyi Qian and Biqing Qi and Xiu Li and Bowen Zhou},
    howpublished = {\url{https://github.com/RyanLiu112/Awesome-Process-Reward-Models}},
    note         = {GitHub repository},
    year         = {2025}
}
Our recent work on LLM test-time scaling with PRMs: 
@article{liu2025can,
    title   = {Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling},
    author  = {Runze Liu and Junqi Gao and Jian Zhao and Kaiyan Zhang and Xiu Li and Biqing Qi and Wanli Ouyang and Bowen Zhou},
    journal = {arXiv preprint arXiv:2502.06703},
    year    = {2025}
}