@article{howtotrainyourdeepresearchagentpromptrew,
  title = {How to Train Your Deep Research Agent? Prompt, Reward, and Policy Optimization in Search-R1},
  author = {Yinuo Xu and Shuo Lu and Jianjie Cheng and Meng Wang and Qianlong Xie and Xingxing Wang and Ran He and Jian Liang},
  year = {2026},
  eprint = {2602.19526},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2602.19526},
}