@article{flowdpoimprovingllmmathematicalreasoning,
  title = {Flow-DPO: Improving LLM Mathematical Reasoning through Online Multi-Agent Learning},
  author = {Yihe Deng and Paul Mineiro},
  year = {2024},
  eprint = {2410.22304},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2410.22304v1},
}