ANVIL: Analogies and Videos for Lecturers

TL;DR

ANVIL is a multimodal system that automates the creation of analogy-based educational animations for computer science, combining natural language processing, visual scripting, and automated quality assessment to support educators.

Contribution

The paper introduces ANVIL, a novel system that automates instructional animation generation using multimodal AI, including scalable quality evaluation methods.

Findings

ANVIL produces educational materials rated as adequate by educators.

Educators respond positively to ANVIL's usability and perceived value.

The system effectively balances pedagogical validity with scalability.

Abstract

We present ANVIL, a multimodal generative system that automates the production of analogy-based instructional animations for computer science topics. Given a concept definition, ANVIL generates a textual analogy, compiles it into a structured visual screenplay, and produces executable manim code to render an animation, with an automated repair mechanism to improve robustness. Evaluating such systems at scale requires balancing pedagogical validity with scalability. We begin with a teacher evaluation to ground the quality assessment and use its findings to guide automated screening. For textual analogies, we introduce an LLM-based evaluator for scalable quality screening; for videos, where subjective judgments are difficult to automate, we instead assess fidelity to the intended screenplay using an automated proxy for auditing and error analysis. We further conduct a user study with educators to examine adoption requirements and risks. Our findings suggest that ANVIL can produce materials that are frequently rated as adequate, and that educators respond positively to its perceived value and usability.