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.
@article{arxiv.2601.06373,
title = {DemMA: Dementia Multi-Turn Dialogue Agent with Expert-Guided Reasoning and Action Simulation},
author = {Yutong Song and Jiang Wu and Kazi Sharif and Honghui Xu and Nikil Dutt and Amir Rahmani},
journal= {arXiv preprint arXiv:2601.06373},
year = {2026}
}