Abstract

While recent generative models advance pixel-space video synthesis, they remain limited in producing professional ecu videos, which demand disciplinary knowledge, precise visual structures, and coherent transitions, limiting their applicabilityl in educational scenarios. Intuitively, such requirements are better addressed through the manipulation of a renderable environment, which can be explicitly controlled via logical commands (e.g., code). In this work, we propose Code2Video, a codecentric agent framework for generating educational videos via executable Python code. The framework comprises three collaborative agents: (i) Planner, which structures lecture content into temporally coherent flows and prepares corresponding visual assets; (ii) Coder, which converts structured instructions into executable Python codes while incorporating scope-guided auto-fix to enhance efficiency; and (iii) Critic, which leverages vision-language models (VLM) with anchor visual prompts to refine spatial layout and ensure clarity. To support systemati evaluation, we build MMMC, a benchmark of professionally produced, long-form, disciplinespecific educational videos. We evaluate MMMC across diverse dimensions, including VLM-as-a-Judge aesthetic scores, code efficiency, and particularly, TeachQuiz, a novel end-to-end knowledge transfer measured by a VLM's ability to learn from the generated videos. Our results demonstrate the potential of Code2Video as a scalable, interpretable, and controllable approach for educational video generation.