On Designing Effective RL Reward at Training Time for LLM Reasoning

@misc{gao2024designingeffectiverl,
      title={On Designing Effective RL Reward at Training Time for LLM Reasoning}, 
      author={Jiaxuan Gao and Yi Wu and Weilin Liu and Shusheng Xu and Wei Fu and Wenjie Ye and Zhiyu Mei and Guangju Wang and Chuyi He},
      year={2024},
      eprint={2410.15115},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/2410.15115}, 
}