The emerging large language model role-playing agents (LLM RPAs) aim to simulate individual human behaviors, but the persona fidelity is often undermined by manually-created profiles (e.g., cherry-picked information and personality characteristics) without validating the alignment with the target individuals. To address this limitation, our work introduces the Dynamic Persona Refinement Framework (DPRF). DPRF aims to optimize the alignment of LLM RPAs' behaviors with those of target individuals by iteratively identifying the cognitive divergence, either through free-form or theory-grounded, structured analysis, between generated behaviors and human ground truth, and refining the persona profile to mitigate these divergences. We evaluate DPRF with five LLMs on four diverse behavior-prediction scenarios: formal debates, social media posts with mental health issues, public interviews, and movie reviews. DPRF can consistently improve behavioral alignment considerably over baseline personas and generalizes across models and scenarios. Our work provides a robust methodology for creating high-fidelity persona profiles and enhancing the validity of downstream applications, such as user simulation, social studies, and personalized AI.

翻译：新兴的大语言模型角色扮演代理（LLM RPAs）旨在模拟个体人类行为，但角色保真度常因手动创建的角色档案（例如精选信息和人格特征）而受损，且未验证其与目标个体的对齐性。为应对这一局限，本研究提出了动态角色精炼框架（DPRF）。DPRF旨在通过迭代识别生成行为与人类真实行为之间的认知差异（采用自由形式或基于理论的、结构化的分析方法），并精炼角色档案以弥合这些差异，从而优化LLM RPAs行为与目标个体行为的对齐。我们在四种不同的行为预测场景（正式辩论、涉及心理健康问题的社交媒体帖子、公开访谈和电影评论）中使用五个大语言模型对DPRF进行评估。DPRF能持续显著提升行为对齐效果，优于基线角色档案，并能在不同模型和场景间泛化。本研究为创建高保真角色档案及增强下游应用（如用户模拟、社会研究和个性化人工智能）的有效性提供了稳健的方法论。