FlipTS: Failure-to-Success Mathematical Self-Refinement via Trajectory-Aware Sampling in End-to-End Online RL

published

Cite this paper

@article{yaqian2026,
  title = {FlipTS: Failure-to-Success Mathematical Self-Refinement via Trajectory-Aware Sampling in End-to-End Online RL},
  author = {Hao, Yaqian and Hao, Yifan and Liu, Yankai and Chao, Fangning and Cui, Zhaojun and Zhang, Haiyu and Bai, Huan and Meng, Fanyu and Deng, Chao and Feng, Junlan},
  journal = {Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing},
  year = {2026},
  month = {Jan},
  doi = {10.18653/2026.emnlp-main.2544},
  url = {https://doi.org/10.18653/2026.emnlp-main.2544},
}