@inproceedings{ruan-etal-2026-self,
    title = "A Self-Evolving {LLM} Agent Framework for Role-Based Norm Compliance in Healthcare",
    author = "Ruan, Haijie  and
      Jiang, Xiaowu  and
      LI, Zhanpeng  and
      Jia, Wei  and
      Xu, Xuanwu  and
      Shan, Xiao-Fen  and
      Chen, Shujie  and
      Ye, Xindong",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.1133/",
    pages = "22562--22577",
    ISBN = "979-8-89176-395-1",
    abstract = "Large language models (LLMs) are increasingly proposed as conversational agents in healthcare, yet many existing systems treat roles as static prompts and rely on one-shot safety filters. In such designs, it can be difficult to enforce long-horizon responsibilities, stable role identity, and realistic communication behavior. We propose a Self-Evolving LLM Agent that learns from role-based social experience and explicitly models communicator-level individual traits informed by prior communication questionnaires and clinical literature. The agent integrates (i) perception and action conditioned on both hard role responsibility norms and soft trait-conditioned style preferences, (ii) structured memory storing norm-annotated trajectories and identity states, (iii) dual-layer reflection that combines short-term responsibility diagnosis with long-term identity drift detection via trait consistency and trait-norm compatibility checks, and (iv) self-evolution that updates system prompts and identity parameters through preference-style optimization with AI feedback. We instantiate the framework in a multi-role healthcare sandbox and evaluate outpatient medication review, emergency triage, and discharge planning. Across our simulated tasks, self-evolution is associated with lower severity-weighted norm risk, more stable role-identity signals, and improved social embeddedness metrics (including trust-like signals) relative to strong static baselines."
}