Synthesizing a Progression of Subtasks for Block-Based Visual Programming Tasks

This paper presents ProgresSyn, an algorithm that synthesizes progressions of subtasks for block-based visual programming tasks (like Hour of Code and Karel), breaking complex problems into simpler steps. The work evaluates this approach both with AI agents (neural program synthesizers) and through a user study with novice K-12 programmers, demonstrating improved task completion rates.

Block-based visual programming environments play an increasingly important role in introducing computing concepts to K-12 students. In recent years, they have also gained popularity in neuro-symbolic AI, serving as a benchmark to evaluate general problem-solving and logical reasoning skills. The open-ended and conceptual nature of these visual programming tasks make them challenging, both for state-of-the-art AI agents as well as for novice programmers. A natural approach to providing assistance

Source

Framework Categories

Tool Types

Tags