@article{improvingdataandrewarddesignforscientifi,
  title = {Improving Data and Reward Design for Scientific Reasoning in Large Language Models},
  author = {Zijie Chen and Zhenghao Lin and Xiao Liu and Zhenzhong Lan and Yeyun Gong and Peng Cheng},
  year = {2026},
  eprint = {2602.08321},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2602.08321},
}