From Passive Consumption to Active Interaction: Exploring Interactive LLM Scaffolding to Support Learning Engagement

TL;DR

This paper investigates embedding lightweight interactive elements into LLM-generated scaffolding to enhance active learner engagement and improve short-term learning outcomes, addressing the passive nature of current LLM-based educational support.

Contribution

It introduces a novel approach of interactive scaffolding in LLMs and provides initial empirical evidence of its effectiveness in promoting engagement and learning.

Findings

Interactive scaffolding increases perceived engagement

It enhances learners' attentional focus

Supports short-term learning performance

Abstract

Large Language Models (LLMs) are increasingly used as learning companions, providing scaffolded explanations, hints, or step-by-step guidance. However, in current LLM-based learning scenarios, scaffolded content is primarily consumed passively, offering limited support for active learner engagement. Learning science research suggests that effective educational scaffolding depends not only on what support is provided, but also on how learners engage with it. In this work, we explore whether embedding lightweight interactive components into LLM-generated scaffolding responses can promote learning-oriented engagement and improve short-term learning outcomes. We evaluated this approach through a within-subjects laboratory study (N=8). Results provide initial evidence that interactive scaffolding increases learners' perceived engagement and attentional focus, while supporting short-term learning performance. We conclude with design implications for integrating interaction into LLM-generated scaffolding to support active learning engagement.