DBox: Scaffolding Algorithmic Programming Learning through Learner-LLM Co-Decomposition

2025-02-26

AI Summary

Existing self-study approaches—such as reference solutions or generic LLM assistance—often deliver overloaded, non-personalized guidance misaligned with learners’ individual problem decomposition strategies, thereby hindering independent problem-solving and critical thinking. To address this, we propose DBox, the first interactive system enabling learner-LLM co-decomposition: it dynamically constructs a stepwise decomposition tree tailored to each learner’s cognitive pace, supporting bidirectional, real-time, scaffolded guidance. DBox integrates three core components: decomposition reasoning, cognitive load–aware feedback, and erroneous strategy analysis. A 24-participant user study demonstrates that DBox significantly improves learning outcomes, cognitive engagement, and critical thinking performance. Participants consistently rated its guidance as highly appropriate and practical, reporting markedly increased self-efficacy and task accomplishment.

Technology Category

• Search and Optimization: Learning to Search
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Cognitive Modeling & Cognitive Systems: Adaptive Behavior

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Decomposition is a fundamental skill in algorithmic programming, requiring learners to break down complex problems into smaller, manageable parts. However, current self-study methods, such as browsing reference solutions or using LLM assistants, often provide excessive or generic assistance that misaligns with learners' decomposition strategies, hindering independent problem-solving and critical thinking. To address this, we introduce Decomposition Box (DBox), an interactive LLM-based system that scaffolds and adapts to learners' personalized construction of a step tree through a"learner-LLM co-decomposition"approach, providing tailored support at an appropriate level. A within-subjects study (N=24) found that compared to the baseline, DBox significantly improved learning gains, cognitive engagement, and critical thinking. Learners also reported a stronger sense of achievement and found the assistance appropriate and helpful for learning. Additionally, we examined DBox's impact on cognitive load, identified usage patterns, and analyzed learners' strategies for managing system errors. We conclude with design implications for future AI-powered tools to better support algorithmic programming education.

Problem

• Scaffolding algorithmic programming learning
• Personalized decomposition strategies
• Enhancing critical thinking skills

Innovation

• LLM-based interactive system
• Learner-LLM co-decomposition
• Personalized step tree construction