@inproceedings{liu-etal-2026-thought,
    title = "Thought-Aware {KV} Cache Compaction for Reasoning via Adaptive Attention Matching",
    author = "Liu, Yang  and
      Chong, Bin  and
      Zhang, Chongyang  and
      Zheng, Hao  and
      Liang, Jiayu  and
      Kefu, Xu",
    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.1605/",
    pages = "34181--34195",
    ISBN = "979-8-89176-462-0"
}