@article{stableandefficientsinglerolloutrlformult,
  title = {Stable and Efficient Single-Rollout RL for Multimodal Reasoning},
  author = {Rui Liu and Dian Yu and Lei Ke and Haolin Liu and Yujun Zhou and Zhenwen Liang and Haitao Mi and Pratap Tokekar and Dong Yu},
  year = {2025},
  eprint = {2512.18215},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2512.18215},
}