@article{beyondtrajectoryimitationstrategyguidedp,
  title = {Beyond Trajectory Imitation: Strategy-Guided Policy Optimization for LLM Reasoning},
  author = {Tianyuan Shi and Canbin Huang and Bei Li and Xin Chen and Xiaojun Quan and Jingang Wang and Qifan Wang},
  year = {2026},
  eprint = {2606.24064},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.24064},
}