StructRAG¶
Product or Programme · All products and programmes
Evidence · 2 claims (2 for) · 1 study (1 design),q1· 0 of 1 report an effect size · 2 claims rest on one study
Description¶
A Sun Y. et al. framework that converts engineering-diagram images into graphs, retrieves structural templates, and uses pattern-aware LLM reasoning to support interpretation, feedback, and automated grading.
Components¶
Claims¶
- Current AI tutoring systems misinterpret complex STEM engineering diagrams, omitting edges, misclassifying component connections, and flattening hierarchical topologies [+W]
- StructRAG achieves 89.3% question-level accuracy and 93.0% edge-level F1 on 1,650 STEM diagram questions, outperforming OCR+CV, GPT-4 graph-only, direct-image GPT-4o, and ablated variants [+M]
Related Products and Programmes¶
- Ground LLM prompts in retrieved structural patterns rather than node labels or keyword matching: the pattern-aware prompt construction inside StructRAG
Key Sources¶
- Sun Y., Liao Y. & Ma X. (2026). Advancing diagram-based reasoning in AI tutoring systems: a structural approach for STEM education. Smart Learning Environments. https://doi.org/10.1186/s40561-026-00459-9
Page metadata
| Field | Value |
|---|---|
type |
product |
id |
structrag |
title |
StructRAG |
description |
A Sun Y. |
status |
review |
product_kind |
framework |
generated |
by process:settle-candidates on 2026-10-11 |
trust |
unverified — no one has confirmed this page's content |
Frontmatter is the page's machine-readable record — see the Schema & Guide.