@inproceedings{fan-etal-2026-llm,
    title = "If an {LLM} Were a Character, Would It Know Its Own Story? Evaluating Lifelong Learning in {LLM}s",
    author = "Fan, Siqi  and
      Huang, Xiusheng  and
      Yao, Yiqun  and
      Fang, Xuezhi  and
      Liu, Kang  and
      Han, Peng  and
      Shang, Shuo  and
      Sun, Aixin  and
      Wang, Yequan",
    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.1659/",
    pages = "35846--35858",
    ISBN = "979-8-89176-390-6",
    abstract = "Large language models (LLMs) can carry out human-like dialogue, but unlike humans, they are stateless due to the superposition property. However, during multi-turn, multi-agent interactions, LLMs begin to exhibit consistent, character-like behaviors{---}hinting at a form of emergent lifelong learning. Despite this, existing benchmarks often fail to capture these dynamics, primarily focusing on static, open-ended evaluations. To address this gap, we introduce LifeState-BENCH, a benchmark designed to assess lifelong learning in LLMs. It features two episodic datasets{---}Hamlet and a synthetic script collection{---}rich in narrative structure and character interactions. Our fact-checking evaluation probes models' self-awareness, episodic memory retrieval, and relationship tracking, across both parametric and non-parametric approaches. Experiments on models like Llama3.1-8B, GPT-4-turbo, and DeepSeek R1, we demonstrate that non-parametric methods significantly outperform parametric ones in managing stateful learning. However, all models exhibit challenges with catastrophic forgetting as interactions extend, highlighting the need for further advancements in lifelong learning."
}