Efficient Process Reward Model Training via Active Learning
April 16, 2025 Β· View on GitHub
Efficient Process Reward Model Training via Active Learning
The official Implementation for Paper "Efficient Process Reward Model Training via Active Learning".
π₯ Updates
- 16/04/2025: Our paper is available on arxiv now!
- 14/04/2025: We release our code, models and data. Paper will be available soon.
- 14/04/2025: Within 7B PRMs, our model
sail/ActPRM-X(based onQwen/Qwen2.5-Math-PRM-7B) achieved new SOTA performance on ProcessBench (76.0%) and PRMBench (66.7%).
π΄σ Άσ ΅σ σ ‘σ °σ Ώ Overview
TL;DR: We achieved SOTA performance on ProcessBench (75.0%) and PRMBench (65.5%) with merely 5% labeling cost compared with Qwen/Qwen2.5-Math-PRM-7B.
π Results
ProcessBench
PRMBench
β‘οΈ Quickstart
Installation
git clone https://github.com/sail-sg/ActivePRM.git
cd ActivePRM
pip install -e . # tested in conda env where python==3.11
Replication
- Evaluate our
sail/ActPRM-Xandsail/ActPRMon ProcessBench simply by running
cd examples
python py_scripts/test_actprm_on_processbench.py
- Training PRM with Active Learning
cd examples
bash scripts/pool_based_active_learning.sh sail/ActPRMData
Citation
If you find our repo or paper helpful, please cite
@misc{duan2025actprm,
title={Efficient Process Reward Model Training via Active Learning},
author={Keyu Duan and Zichen Liu and Xin Mao and Tianyu Pang and Changyu Chen and Qiguang Chen and Michael Qizhe Shieh and Longxu Dou},
year={2025},
eprint={2504.10559},
archivePrefix={arXiv},
primaryClass={cs.LG},
url={https://arxiv.org/abs/2504.10559},
}