ReMe: Scaffolding Personalized Cognitive Training via Controllable LLM-Mediated Conversations

TL;DR

ReMe is a web-based framework that uses controllable large language models to create personalized, engaging cognitive training conversations for older adults, addressing rigidity and personalization issues in traditional programs.

Contribution

The paper introduces ReMe, a modular system that scaffolds personalized cognitive training via controllable LLM-mediated conversations, integrating structured puzzles and personal life logs.

Findings

Community pilot with 32 adults aged 50+ shows initial feasibility.

ReMe enables rapid development of personalized dialogue-based cognitive tasks.

The framework effectively combines structured puzzles with personal memory activities.

Abstract

Global aging calls for scalable and engaging cognitive interventions. Computerized cognitive training (CCT) is a promising non-pharmacological approach, yet many unsupervised programs rely on rigid, hand-authored puzzles that are difficult to personalize and can hinder adherence. Large language models (LLMs) offer more natural interaction, but their open-ended generation complicates the controlled task structure required for cognitive training. We present ReMe, a web-based framework that scaffolds cognitive training through controllable LLM-mediated conversations, addressing both rigidity in conventional CCT content and the need for conversational controllability. ReMe features a modular Puzzle Engine that represents training activities as reusable puzzle groups specified by structured templates and constraint rules, enabling rapid development of dialogue-based word games and personalized tasks grounded in user context. By integrating personal life logs, ReMe supports Life Recall activities for episodic-memory practice through guided retrieval and progressive cues. A community pilot with 32 adults aged 50+ provides initial feasibility signals.