@inproceedings{wang-etal-2026-listen, title = "Listen, Pause, and Reason: Toward Perception-Grounded Hybrid Reasoning for Audio Understanding", author = "Wang, Jieyi and Niu, Yazhe and Xu, Dexuan and Wei, Zhongyu", 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.1776/", pages = "35653--35671", ISBN = "979-8-89176-395-1" }