Large Language Models (LLMs) acting as artificial agents offer the potential for scalable behavioral research, yet their validity depends on whether LLMs can maintain stable personas across extended conversations. We address this point using a dual-assessment framework measuring both self-reported characteristics and observer-rated persona expression. Across two experiments testing four persona conditions (default, high, moderate, and low ADHD presentations), seven LLMs, and three semantically equivalent persona prompts, we examine between-conversation stability (3,473 conversations) and within-conversation stability (1,370 conversations and 18 turns). Self-reports remain highly stable both between and within conversations. However, observer ratings reveal a tendency for persona expressions to decline during extended conversations. These findings suggest that persona-instructed LLMs produce stable, persona-aligned self-reports, an important prerequisite for behavioral research, while identifying this regression tendency as a boundary condition for multi-agent social simulation.

翻译：大型语言模型（LLMs）作为人工代理具有可扩展行为研究的潜力，但其有效性取决于LLMs是否能在长时间对话中保持稳定的角色。我们采用一个双重评估框架来解决这一问题，该框架同时测量自我报告的特征和观察者评定的角色表达。通过两项实验，测试了四种角色条件（默认、高、中、低ADHD表现）、七个LLM和三个语义等价角色提示，我们考察了对话间稳定性（3,473次对话）和对话内稳定性（1,370次对话和18轮对话）。自我报告在对话间和对话内均保持高度稳定。然而，观察者评分揭示，在长时间对话中角色表达有下降趋势。这些发现表明，角色指令化的LLM能产生稳定的、与角色一致的自我报告，这是行为研究的重要前提，同时指出了这种回归趋势作为多智能体社会模拟的一个边界条件。