@inproceedings{yang-etal-2026-llm-cache,
    title = "{LLM} Cache Bandits with Query Heterogeneity for Cost-Efficient Inference",
    author = "Yang, Hantao  and
      Xie, Hong  and
      Liu, Xutong  and
      Lian, Defu",
    editor = "Lee, Hung-Yi  and
      Dev, Sunipa  and
      Li, Jessy  and
      Elliott, Desmond",
    booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.emnlp-main.1849/",
    pages = "42054--42087",
    ISBN = "979-8-89176-459-0"
}