@article{branposcalablecontrastivebranchsamplingf,
  title = {BranPO: Scalable Contrastive Branch Sampling for Long-Horizon Agentic Reinforcement Learning},
  author = {Yubao Zhao and Weiquan Huang and Sudong Wang and Ruochen Zhao and Chen Chen and Yao Shu and Chengwei Qin},
  year = {2026},
  eprint = {2602.03719},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2602.03719},
}