@inproceedings{hu-etal-2026-clonemem,
    title = "{C}lone{M}em: Benchmarking Long-Term Memory for {AI} Clones",
    author = "Hu, Sen  and
      Zhang, Zhiyu  and
      Wei, Yuxiang  and
      Han, Xueran  and
      Tang, Zhenheng  and
      Chen, Ronghao  and
      Wang, Huacan",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.1549/",
    pages = "33571--33602",
    ISBN = "979-8-89176-390-6",
    abstract = "AI Clones aim to simulate an individual{'}s thoughts and behaviors to enable long-term, personalized interaction, placing stringent demands on memory systems to model experiences, emotions, and opinions over time. Existing memory benchmarks primarily rely on user{--}agent conversational histories, which are temporally fragmented and insufficient for capturing continuous life trajectories. We introduce CloneMem, a benchmark for evaluating long-term memory in AI Clone scenarios grounded in non-conversational digital traces, including diaries, social media posts, and emails, spanning one to three years. CloneMem adopts a top-down data construction framework to ensure longitudinal coherence and defines tasks that assess an agent{'}s ability to track evolving personal states. Experiments show that current memory mechanisms struggle in this setting, highlighting open challenges for life-grounded personalized AI. Code and dataset are available at https://github.com/AvatarMemory/CloneMemBench"
}