From EduVisBench to EduVisAgent: A Benchmark and Multi-Agent Framework for Reasoning-Driven Pedagogical Visualization

TL;DR

This paper introduces EduVisBench, a comprehensive benchmark for evaluating visual reasoning in educational models, and EduVisAgent, a multi-agent framework that significantly improves pedagogical visualizations by coordinating specialized agents.

Contribution

The paper presents EduVisBench for assessing visual reasoning in educational models and proposes EduVisAgent, a multi-agent system that enhances visualization quality and reasoning capabilities.

Findings

Existing models struggle with visual reasoning and decomposition.

EduVisAgent outperforms baselines with a 40.2% improvement.

EduVisAgent produces more educationally aligned visualizations.

Abstract

While foundation models (FMs), such as diffusion models and large vision-language models (LVLMs), have been widely applied in educational contexts, their ability to generate pedagogically effective visual explanations remains limited. Most existing approaches focus primarily on textual reasoning, overlooking the critical role of structured and interpretable visualizations in supporting conceptual understanding. To better assess the visual reasoning capabilities of FMs in educational settings, we introduce EduVisBench, a multi-domain, multi-level benchmark. EduVisBench features diverse STEM problem sets requiring visually grounded solutions, along with a fine-grained evaluation rubric informed by pedagogical theory. Our empirical analysis reveals that existing models frequently struggle with the inherent challenge of decomposing complex reasoning and translating it into visual representations aligned with human cognitive processes. To address these limitations, we propose EduVisAgent, a multi-agent collaborative framework that coordinates specialized agents for instructional planning, reasoning decomposition, metacognitive prompting, and visualization design. Experimental results show that EduVisAgent substantially outperforms all baselines, achieving a 40.2% improvement and delivering more educationally aligned visualizations. EduVisBench and EduVisAgent are available at https://github.com/aiming-lab/EduVisBench and https://github.com/aiming-lab/EduVisAgent.