# Code2Video: A Code-centric Paradigm for Educational Video Generation

arXiv: https://arxiv.org/abs/2510.01174 · HTML: https://mlsanity.com/paper/2510.01174/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 53 references that are in the map.
- First posted on arXiv 1 Oct 2025.

## Builds on (most cited first, 30 of 42)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [Video Diffusion Models](https://mlsanity.com/paper/2204.03458/) (2022)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [Imagen Video: High Definition Video Generation with Diffusion Models](https://mlsanity.com/paper/2210.02303/) (2022)
- [Gorilla: Large Language Model Connected with Massive APIs](https://mlsanity.com/paper/2305.15334/) (2023)
- [Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models](https://mlsanity.com/paper/2402.17177/) (2024)
- [SpatialRGPT: Grounded Spatial Reasoning in Vision Language Models](https://mlsanity.com/paper/2406.01584/) (2024)
- [StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation](https://mlsanity.com/paper/2405.01434/) (2024)
- [ShowUI: One Vision-Language-Action Model for GUI Visual Agent](https://mlsanity.com/paper/2411.17465/) (2024)
- [Open-Sora 2.0: Training a Commercial-Level Video Generation Model in 200k](https://mlsanity.com/paper/2503.09642/) (2025)
- [Make-Your-Video: Customized Video Generation Using Textual and Structural Guidance](https://mlsanity.com/paper/2306.00943/) (2023)
- [Long-Context Autoregressive Video Modeling with Next-Frame Prediction](https://mlsanity.com/paper/2503.19325/) (2025)
- [Loong: Generating Minute-level Long Videos with Autoregressive Language Models](https://mlsanity.com/paper/2410.02757/) (2024)
- [ChartCoder: Advancing Multimodal Large Language Model for Chart-to-Code Generation](https://mlsanity.com/paper/2501.06598/) (2025)
- [FreeLong: Training-Free Long Video Generation with SpectralBlend Temporal Attention](https://mlsanity.com/paper/2407.19918/) (2024)
- [ARTboldsymbol·V: Auto-Regressive Text-to-Video Generation with Diffusion Models](https://mlsanity.com/paper/2311.18834/) (2023)
- [A Review of Prominent Paradigms for LLM-Based Agents: Tool Use (Including RAG), Planning, and Feedback Learning](https://mlsanity.com/paper/2406.05804/) (2024)
- [Progressive Autoregressive Video Diffusion Models](https://mlsanity.com/paper/2410.08151/) (2024)
- [Paper2Poster: Towards Multimodal Poster Automation from Scientific Papers](https://mlsanity.com/paper/2505.21497/) (2025)
- [Mora: Enabling Generalist Video Generation via A Multi-Agent Framework](https://mlsanity.com/paper/2403.13248/) (2024)
- [How to Enable LLM with 3D Capacity? A Survey of Spatial Reasoning in LLM](https://mlsanity.com/paper/2504.05786/) (2025)
- [ARLON: Boosting Diffusion Transformers with Autoregressive Models for Long Video Generation](https://mlsanity.com/paper/2410.20502/) (2024)
- [A Survey on Long Video Generation: Challenges, Methods, and Prospects](https://mlsanity.com/paper/2403.16407/) (2024)
- [DreamFactory: Pioneering Multi-Scene Long Video Generation with a Multi-Agent Framework](https://mlsanity.com/paper/2408.11788/) (2024)
- [StoryAgent: Customized Storytelling Video Generation via Multi-Agent Collaboration](https://mlsanity.com/paper/2411.04925/) (2024)
- [From Words to Structured Visuals: A Benchmark and Framework for Text-to-Diagram Generation and Editing](https://mlsanity.com/paper/2411.11916/) (2024)
- [ProjectEval: A Benchmark for Programming Agents Automated Evaluation on Project-Level Code Generation](https://mlsanity.com/paper/2503.07010/) (2025)
- [TheoremExplainAgent: Towards Video-based Multimodal Explanations for LLM Theorem Understanding](https://mlsanity.com/paper/2502.19400/) (2025)

## Built on by (most cited first, 27 of 27)

- [Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond](https://mlsanity.com/paper/2604.22748/) (2026)
- [Beyond NL2Code: A Structured Survey of Multimodal Code Intelligence](https://mlsanity.com/paper/2606.15932/) (2026)
- [Beyond End-to-End Video Models: An LLM-Based Multi-Agent System for Educational Video Generation](https://mlsanity.com/paper/2602.11790/) (2026)
- [IMAGAgent: Orchestrating Multi-Turn Image Editing via Constraint-Aware Planning and Reflection](https://mlsanity.com/paper/2603.29602/) (2026)
- [ManiBench: A Benchmark for Testing Visual-Logic Drift and Syntactic Hallucinations in Manim Code Generation](https://mlsanity.com/paper/2603.13251/) (2026)
- [How Far Are Vision-Language Models from Constructing the Real World? A Benchmark for Physical Generative Reasoning](https://mlsanity.com/paper/2603.24866/) (2026)
- [ViviDoc: Generating Interactive Documents through Human-Agent Collaboration](https://mlsanity.com/paper/2603.27991/) (2026)
- [EvoDiagram: Agentic Editable Diagram Creation via Design Expertise Evolution](https://mlsanity.com/paper/2604.09568/) (2026)
- [Training and Agentic Inference Strategies for LLM-based Manim Animation Generation](https://mlsanity.com/paper/2604.18364/) (2026)
- [ManimAgent: Self-Evolving Multimodal Agents for Visual Education](https://mlsanity.com/paper/2606.30296/) (2026)
- [TeachMaster: Generative Teaching via Code](https://mlsanity.com/paper/2601.04204/) (2025)
- [EduIllustrate: Towards Scalable Automated Generation Of Multimodal Educational Content](https://mlsanity.com/paper/2604.05005/) (2026)
- [ANVIL: Analogies and Videos for Lecturers](https://mlsanity.com/paper/2605.16295/) (2026)
- [PRISM: A Benchmark for Programmatic Spatial-Temporal Reasoning](https://mlsanity.com/paper/2605.19382/) (2026)
- [Supervise What Survives: Geometry-Guided VLA Adaptation from Synthetic Robot Videos](https://mlsanity.com/paper/2606.24448/) (2026)
- [Findings of the First Teaching Monster Challenge: A Benchmark of Pedagogical Content Knowledge in AI Agents](https://mlsanity.com/paper/2608.08852/) (2026)
- [RULER: Instance-aware Rubric Rewards for SVG Generation](https://mlsanity.com/paper/2609.25270/) (2026)
- [Demonstrating ViviDoc: Generating Interactive Documents through Human-Agent Collaboration](https://mlsanity.com/paper/2603.01912/) (2026)
- [ALGOGEN: Tool-Generated Verifiable Traces for Reliable Algorithm Visualization](https://mlsanity.com/paper/2605.12159/) (2026)
- [See Before You Code: Learning Visual Priors for Spatially Aware Educational Animation Generation](https://mlsanity.com/paper/2605.15585/) (2026)
- [Helping Figures Tell their Story! Paper-Grounded Video Generation Explaining Complex Scientific Figures](https://mlsanity.com/paper/2606.12576/) (2026)
- [SGA: Plug&Play Geometric Verification for Educational Video Synthesis](https://mlsanity.com/paper/2607.18116/) (2026)
- [EduPanel: A Three-Agent LLM Judge for Teaching Videos -- Reliability, Complementarity, and Human Trust Calibration](https://mlsanity.com/paper/2607.18529/) (2026)
- [From Content Generation to Learning Support: Pedagogy-Guided Generative Video Tutors for STEM Learning](https://mlsanity.com/paper/2609.24083/) (2026)
- [Recursive Game Creator: An Agentic Product-Level Experience-Oriented Game Harness](https://mlsanity.com/paper/2610.08621/) (2026)
- [Reels-RSI: Program-Level Self-Improvement for Code-Rendered Explainer Videos](https://mlsanity.com/paper/2610.14495/) (2026)
- [SpecForge: Recursive Self-Improvement for Coding Agents via Behavioral Specifications](https://mlsanity.com/paper/2610.15708/) (2026)

## Abstract (arXiv)

While recent generative models advance pixel-space video synthesis, they remain limited in producing professional educational videos, which demand disciplinary knowledge, precise visual structures, and coherent transitions, limiting their applicability 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 code-centric 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 visual anchor prompts to refine spatial layout and ensure clarity. To support systematic evaluation, we build MMMC, a benchmark of professionally produced, discipline-specific 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 metric that quantifies how well a VLM, after unlearning, can recover knowledge by watching the generated videos. Our results demonstrate the potential of Code2Video as a scalable, interpretable, and controllable approach, achieving 40% improvement over direct code generation and producing videos comparable to human-crafted tutorials. The code and datasets are available at https://github.com/showlab/Code2Video.