@article{plannerr1rewardshapingenablesefficientag,
  title = {Planner-R1: Reward Shaping Enables Efficient Agentic RL with Smaller LLMs},
  author = {Siyu Zhu and Yanbin Jiang and Hejian Sang and Shao Tang and Qingquan Song and Biao He and Rohit Jain and Zhipeng Wang and Alborz Geramifard},
  year = {2025},
  eprint = {2509.25779},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2509.25779},
}