Stitch: Step-by-step LLM Guided Tutoring for Scratch

TL;DR

Stitch is an interactive tutoring system for Scratch that uses step-by-step guidance and large language models to help learners understand and fix semantic bugs, improving programming education effectiveness.

Contribution

The paper introduces Stitch, a novel LLM-guided, step-by-step tutoring system that enhances Scratch learning by providing critical difference explanations instead of direct answers.

Findings

Step-by-step guidance improves learning outcomes.

Stitch outperforms automated feedback tools.

Interactive explanations foster better understanding.

Abstract

Block-based environments such as Scratch are increasingly popular in programming education. While block syntax reduces surface errors, semantic bugs remain common and challenging for novices to resolve. Existing debugging workflows typically show the correct program directly to learners, a strategy that may fix errors but undermines the development of problem-solving skills. We present Stitch, an interactive tutoring system that replaces "showing the answer" with step-by-step scaffolding. The system's Diff-Analyze module contrasts a student's project with a reference implementation, identifies the most critical differences, and uses a large language model to explain why these changes matter. Learners inspect highlighted blocks through a custom rendering engine, understand the explanations, and selectively apply partial fixes. This iterative process continues until the intended functionality is achieved. We evaluate Stitch in an empirical study, comparing it against a state-of-the-art automated feedback generation tool for Scratch. Our key insight is that simply presenting the correct program is pedagogically ineffective. In contrast, our interactive, step-by-step guided system promotes a more effective learning experience. More broadly, what constitutes effective feedback in block-based programming remains an open question. Our evaluation provides new evidence that step-by-step tutoring significantly enhances learning outcomes, outperforming both direct-answer approaches and current automated feedback generation tools.