@article{answerconsistentchainofthoughtreinforcem,
  title = {Answer-Consistent Chain-of-thought Reinforcement Learning For Multi-modal Large Langauge Models},
  author = {Minbin Huang and Runhui Huang and Chuanyang Zheng and Jingyao Li and Guoxuan Chen and Han Shi and Hong Cheng},
  year = {2025},
  eprint = {2510.10104},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2510.10104},
}