An Educator-Guided LLM Pedagogical Agent for Scaffolded Feedback in Conceptual Database Design

2026-09-30

AI Summary

This study addresses the lack of personalized, phased feedback in conceptual database design by proposing a large language model-based pedagogical agent integrated into an ERD editor. Its core innovation lies in decoupling a hidden diagnostic architecture from a visible support layer, combining multi-source information grounding with stateful turn management to deliver four-stage progressive scaffolding—from conceptual checking to localized clarification. Across 383 feedback turns, 71.1% of target revisions adopted recommendations derived from the hidden diagnostics. Furthermore, user studies indicate that the delayed disclosure mechanism effectively enhances student autonomy, validating the pedagogical value of the proposed architecture.

Abstract

We present an educator-guided LLM pedagogical agent for scaffolded feedback in conceptual database design. Integrated into an entity--relationship diagram (ERD) editor, the system grounds feedback in the student artifact, assignment requirements, educator-authored rubrics, and instructional resources. Its architecture separates hidden, artifact-grounded diagnosis from the workflow that controls the form and disclosure level of student-facing support. We instantiate the architecture as a four-stage workflow progressing from concept checks and guided application to low-detail feedback and localized clarification. Each feedback request creates a stateful episode linked to versioned ERD states. In a deployment spanning three ERD environments and 383 feedback episodes, 71.1\% of observed target-level changes fully or partially incorporated the hidden diagnostic target, including many after Stages~1--2. Qualitative analysis showed that staged disclosure sometimes withheld inaccurate details, supported selective uptake, or allowed later recovery, though some errors still shaped revisions. Survey responses from a self-selected sample favored delayed disclosure and student agency but noted indirectness and repetition.

Problem

• Conceptual Database Design
• Scaffolded Feedback
• Pedagogical Agent
• Entity-Relationship Diagram
• Large Language Model

Innovation

• Scaffolded Feedback
• Pedagogical Agent
• Large Language Model
• Entity-Relationship Diagram
• Staged Disclosure