@inproceedings{wang-etal-2026-dont, title = "Don{'}t Tell the Answer, Truly Guide the Reasoning During {RL} Rollouts", author = "Wang, Xinyi and Han, Jinyi and Jiang, Zishang and li, Tingyun and Liang, Jiaqing and Jiang, Sihang and Dai, Zhaoqian and Shuguang, Ma and Yu, Fei and Xiao, Yanghua", editor = "Liakata, Maria and Moreira, Viviane P. and Zhang, Jiajun and Jurgens, David", booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026", month = jul, year = "2026", address = "San Diego, California, United States", publisher = "Association for Computational Linguistics", url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.169/", pages = "3437--3455", ISBN = "979-8-89176-395-1" }