SketchMind: A Multi-Agent Cognitive Framework for Assessing Student-Drawn Scientific Sketches

TL;DR

SketchMind is a multi-agent AI framework that assesses and improves student-drawn scientific sketches, offering interpretability, pedagogical alignment, and personalized feedback to enhance conceptual understanding.

Contribution

We introduce SketchMind, a novel multi-agent framework that enables transparent, adaptable, and pedagogically aligned assessment of scientific sketches, outperforming baseline models.

Findings

Achieved 77.1% accuracy on student sketches, a 21.4% improvement over baseline.

Multi-agent orchestration with SRG enhances performance over single-agent systems.

Human evaluators rated SketchMind-generated feedback highly, supporting its educational potential.

Abstract

Scientific sketches (e.g., models) offer a powerful lens into students' conceptual understanding, yet AI-powered automated assessment of such free-form, visually diverse artifacts remains a critical challenge. Existing solutions often treat sketch evaluation as either an image classification task or monolithic vision-language models, which lack interpretability, pedagogical alignment, and adaptability across cognitive levels. To address these limitations, we present SketchMind, a cognitively grounded, multi-agent framework for evaluating and improving student-drawn scientific sketches. SketchMind comprises modular agents responsible for rubric parsing, sketch perception, cognitive alignment, and iterative feedback with sketch modification, enabling personalized and transparent evaluation. We evaluate SketchMind on a curated dataset of 3,575 student-generated sketches across six science assessment items with different highest order of Bloom's level that require students to draw models to explain phenomena. Compared to baseline GPT-4o performance without SRG (average accuracy: 55.6%), and with SRG integration achieves 77.1% average accuracy (+21.4% average absolute gain). We also demonstrate that multi-agent orchestration with SRG enhances SketchMind performance, for example, GPT-4.1 gains an average 8.9% increase in sketch prediction accuracy, outperforming single-agent pipelines across all items. Human evaluators rated the feedback and co-created sketches generated by \textsc{SketchMind} with GPT-4.1, which achieved an average of 4.1 out of 5, significantly higher than those of baseline models (e.g., 2.3 for GPT-4o). Experts noted the system's potential to meaningfully support conceptual growth through guided revision. Our code and (pending approval) dataset will be released to support reproducibility and future research in AI-driven education.