@article{
pan2026reward,
title={Reward Modeling for Reinforcement Learning-Based {LLM} Reasoning: Design, Challenges, and Evaluation},
author={Pei-Chi Pan and Yingbin Liang and Sen Lin},
journal={Transactions on Machine Learning Research},
issn={2835-8856},
year={2026},
url={https://openreview.net/forum?id=TDfrN1TbGH},
note={}
}