@article{steppostepalignedpolicyoptimizationforag,
  title = {StepPO: Step-Aligned Policy Optimization for Agentic Reinforcement Learning},
  author = {Daoyu Wang and Qingchuan Li and Mingyue Cheng and Jie Ouyang and Shuo Yu and Qi Liu and Enhong Chen},
  year = {2026},
  eprint = {2604.18401},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2604.18401},
}