MAGMA-Edu: Multi-Agent Generative Multimodal Framework for Text-Diagram Educational Question Generation

TL;DR

MAGMA-Edu is a multi-agent framework that enhances educational question generation by integrating textual reasoning and diagrammatic synthesis through a self-reflective, iterative process, significantly improving pedagogical coherence and multimodal consistency.

Contribution

It introduces a novel multi-agent, self-reflective pipeline for structured multimodal educational question generation, outperforming existing models in accuracy and consistency.

Findings

Significantly improves textual and image-text metrics over state-of-the-art models.

Achieves new benchmarks in multimodal educational content quality.

Demonstrates the effectiveness of self-reflective multi-agent collaboration.

Abstract

Educational illustrations play a central role in communicating abstract concepts, yet current multimodal large language models (MLLMs) remain limited in producing pedagogically coherent and semantically consistent educational visuals. We introduce MAGMA-Edu, a self-reflective multi-agent framework that unifies textual reasoning and diagrammatic synthesis for structured educational problem generation. Unlike existing methods that treat text and image generation independently, MAGMA-Edu employs a two-stage co-evolutionary pipeline: (1) a generation-verification-reflection loop that iteratively refines question statements and solutions for mathematical accuracy, and (2) a code-based intermediate representation that enforces geometric fidelity and semantic alignment during image rendering. Both stages are guided by internal self-reflection modules that evaluate and revise outputs until domain-specific pedagogical constraints are met. Extensive experiments on multimodal educational benchmarks demonstrate the superiority of MAGMA-Edu over state-of-the-art MLLMs. Compared to GPT-4o, MAGMA-Edu improves the average textual metric from 57.01 to 92.31 (+35.3 pp) and boosts image-text consistency (ITC) from 13.20 to 85.24 (+72 pp). Across all model backbones, MAGMA-Edu achieves the highest scores (Avg-Text 96.20, ITC 99.12), establishing a new state of the art for multimodal educational content generation and demonstrating the effectiveness of self-reflective multi-agent collaboration in pedagogically aligned vision-language reasoning.