A large language model-based self-learning and critical agent framework for multimodal Alzheimer’s disease diagnosis.

A label-free LLM multiagent approach can integrate heterogeneous modalities, retain diagnostic "experience," and generate transparent reasoning while delivering competitive accuracy on ADNI. The framework shows promise for real-world support of complex neuropsychological diagnosis; future work should incorporate fully multimodal LLMs for imaging and repeated, graph-driven iterations to further enhance performance. (PsycInfo Database Record (c) 2026 APA, all rights reserved).