@inproceedings{qi-etal-2026-beyond,
    title = "Beyond Static Persona Consistency: Dynamic Persona Coherence in {LLM} Role-Playing",
    author = "QI, Yirui  and
      Zhang, Xiaoming  and
      Zeng, Ruilin  and
      Liu, Mengyao  and
      Zhou, Ziyi  and
      Miao, Dezhuang  and
      Yan, Bingyu  and
      Guan, Zhenyu",
    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.1336/",
    pages = "28942--28956",
    ISBN = "979-8-89176-390-6",
    abstract = "Current LLM role-playing systems model persona as a monolithic, static attribute, conflating identity consistency with emotional rigidity. This leads to either robotic repetition or catastrophic persona drift under sustained interaction. We introduce Dynamic Persona Coherence, a framework that decouples Identity-Layer Stability (time-invariant traits) from Adaptive-Layer Appropriateness (history-dependent psychological evolution). We operationalize this through the L/M/S Psychological State Model, which represents persona dynamics across long-term identity, mid-term meaning/stress accumulation, and short-term affect. On top of this state representation, a closed-loop alignment system comprising an automated evaluator (Persona Consistency Critic, PCC), a selective repository (Persona Case Repository, PCR), and a trajectory-adjusting corrector (Persona Drift Suppressor, PDS) enables autonomous coherence repair. Experiments on GPT-4o, Claude-3.5-Sonnet, and DeepSeek-V3.2 demonstrate consistent improvements (+16{--}84{\%} PCC gains)."
}