@inproceedings{guo-etal-2026-g2rpo, title = "{G}$^2${RPO}-A: Guided Group Relative Policy Optimization with Adaptive Guidance", author = "Guo, Yongxin and Deng, Wenbo and Cheng, Zhenglin and Tang, Xiaoying", editor = "Liakata, Maria and Moreira, Viviane P. and Zhang, Jiajun and Jurgens, David", booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)", month = jul, year = "2026", address = "San Diego, California, United States", publisher = "Association for Computational Linguistics", url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.206/", pages = "4525--4539", ISBN = "979-8-89176-390-6" }