@inproceedings{wang-etal-2026-apex, title = "{APEX} : Adaptively Balancing Off-Policy Guidance and On-Policy Exploration for {LLM} Reasoning", author = "Wang, Yuchen and Zhang, Zikang and Xu, Duo and Xu, Kunpeng and Zhu, Qihui and Huang, Wei and Wu, Siying and Cheng, Caihong and He, Xin and Yang, Yang and Jiang, Guanjun and Sun, Xiaoyan", editor = "Lee, Hung-Yi and Dev, Sunipa and Li, Jessy and Elliott, Desmond", booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026", month = oct, year = "2026", address = "Budapest, Hungary", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2026.findings-emnlp.329/", pages = "6964--6975", ISBN = "979-8-89176-462-0" }