@article{cm2reinforcementlearningwithchecklistrew,
  title = {CM2: Reinforcement Learning with Checklist Rewards for Multi-Turn and Multi-Step Agentic Tool Use},
  author = {Zhen Zhang and Kaiqiang Song and Xun Wang and Yebowen Hu and Weixiang Yan and Chenyang Zhao and Henry Peng Zou and Haoyun Deng and Sathish Reddy Indurthi and Shujian Liu and Simin Ma and Xiaoyang Wang and Xin Eric Wang and Song Wang},
  year = {2026},
  eprint = {2602.12268},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2602.12268},
}