@article{distillingtheimplicitmultibranch, title = {Distilling the Implicit Multi-Branch Structure in LLMs' Reasoning via Reinforcement Learning}, author = {Shicheng Xu and Liang Pang and Yunchang Zhu and Jia Gu and Zihao Wei and Jingcheng Deng and Feiyang Pan and HuaWei Shen and Xueqi Cheng}, year = {2025}, eprint = {2505.16142}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.16142v1}, }