@inproceedings{meng-etal-2026-autodata, title = "{A}uto{D}ata: Agentic Search for Pre-training Data Selection", author = "Meng, Yan and Srikanth, Dhruv and Zhao, Bingchen and Jiang, Zhengyao and Wu, Yuxiang", 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.2131/", pages = "45474--45491", ISBN = "979-8-89176-462-0" }