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

2025-05-22

AI Summary

Existing foundation models—such as diffusion models and large vision-language models (LVLMs)—generate educational visualizations that lack structural organization and interpretability, hindering conceptual understanding. Method: We propose EduVisBench, the first multi-domain, multi-level benchmark for educational visualization evaluation, and introduce EduVisAgent, a pedagogy-driven multi-agent framework integrating four specialized roles: instructional planning, reasoning decomposition, metacognitive prompting, and visualization design. The framework synergistically combines LVLMs, diffusion models, and education-theory-informed evaluation paradigms, emphasizing cognitive alignment and pedagogical appropriateness to produce structured, interpretable visualizations. Contribution/Results: EduVisAgent achieves a 40.2% improvement over baseline methods, significantly enhancing conceptual interpretability, pedagogical suitability, and cognitive consistency—demonstrating its effectiveness in advancing AI-supported educational visualization.

Technology Category

• Computer Vision: Visual Reasoning & Symbolic Representations
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Web Mining and Content Analysis: Web data visualization

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.

Problem

• Assessing visual reasoning in educational foundation models
• Overcoming limitations in pedagogically effective visualization generation
• Enhancing structured visual explanations for conceptual understanding

Innovation

• Introduces EduVisBench for assessing visual reasoning
• Proposes EduVisAgent multi-agent collaborative framework
• Achieves 40.2% improvement in educational visualizations