@article{roundtripreinforcementlearningselfconsis,
  title = {Round-trip Reinforcement Learning: Self-Consistent Training for Better Chemical LLMs},
  author = {Lecheng Kong and Xiyuan Wang and Yixin Chen and Muhan Zhang},
  year = {2025},
  eprint = {2510.01527},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2510.01527},
}