@article{decorldecouplingreasoningchainsviaparall,
  title = {DeCoRL: Decoupling Reasoning Chains via Parallel Sub-Step Generation and Cascaded Reinforcement for Interpretable and Scalable RLHF},
  author = {Ziyuan Gao and Di Liang and Xianjie Wu and Philippe Morel and Minlong Peng},
  year = {2025},
  eprint = {2511.19097},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2511.19097},
}