@inproceedings{bai-etal-2026-ttvs, title = "{TTVS}: Boosting Self-Exploring Reinforcement Learning via Test-time Variational Synthesis", author = "Bai, Sikai and Li, Haoxi and Zhang, Jie and Liu, Yongjiang and Guo, Song", 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.1634/", pages = "32651--32665", ISBN = "979-8-89176-395-1" }