@article{treeopooffpolicymontecarlotreeguidedadva,
  title = {Tree-OPO: Off-policy Monte Carlo Tree-Guided Advantage Optimization for Multistep Reasoning},
  author = {Bingning Huang and Tu Nguyen and Matthieu Zimmer},
  year = {2025},
  eprint = {2509.09284},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2509.09284},
}