Simulating dementia patients with large language models (LLMs) is challenging due to the need to jointly model cognitive impairment, emotional dynamics, and nonverbal behaviors over long conversations. We present DemMA, an expert-guided dementia dialogue agent for high-fidelity multi-turn patient simulation. DemMA constructs clinically grounded dementia personas by integrating pathology information, personality traits, and subtype-specific memory-status personas informed by clinical experts. To move beyond text-only simulation, DemMA explicitly models nonverbal behaviors, including motion, facial expressions, and vocal cues. We further introduce a Chain-of-Thought distillation framework that trains a single LLM to jointly generate reasoning traces, patient utterances, and aligned behavioral actions within one forward pass, enabling efficient deployment without multi-agent inference. Extensive evaluations with experts, medical students, and LLM judges demonstrate that DemMA significantly outperforms strong baselines across multiple metrics.

翻译：利用大语言模型模拟痴呆症患者具有挑战性，因为需要在长对话中联合建模认知障碍、情绪动态和非语言行为。我们提出了DemMA，一种专家引导的痴呆症对话智能体，用于实现高保真度的多轮患者模拟。DemMA通过整合病理信息、人格特质以及由临床专家指导的亚型特异性记忆状态角色，构建了基于临床依据的痴呆症角色画像。为了超越纯文本模拟，DemMA显式地建模了包括动作、面部表情和声音线索在内的非语言行为。我们进一步引入了一种思维链蒸馏框架，该框架训练单一的大语言模型在一次前向传播中联合生成推理轨迹、患者话语以及对齐的行为动作，从而无需多智能体推理即可实现高效部署。通过专家、医学生和大语言模型评判者进行的广泛评估表明，DemMA在多项指标上显著优于现有基线模型。