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

arXiv: https://arxiv.org/abs/2610.00870 · HTML: https://mlsanity.com/paper/2610.00870/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Educational agents and math problem solving, one of 16 directions in LLM agents and tool use.
- Builds on 5 of its 45 references that are in the map.
- First posted on arXiv 1 Oct 2026.

## Placed in

- LLM agents and tool use / [Educational agents and math problem solving](https://mlsanity.com/agents/educational-agents-and-math-problem-solving/)

## Builds on (most cited first, 5 of 5)

- [Prototyping the use of Large Language Models (LLMs) for adult learning content creation at scale](https://mlsanity.com/paper/2306.01815/) (2023)
- [FACET: Teacher-Centred LLM-Based Multi-Agent Systems-Towards Personalized Educational Worksheets](https://mlsanity.com/paper/2508.11401/) (2025)
- [Towards Adaptive Feedback with AI: Comparing the Feedback Quality of LLMs and Teachers on Experimentation Protocols](https://mlsanity.com/paper/2502.12842/) (2025)
- [Are Large Language Models Fit For Guided Reading?](https://mlsanity.com/paper/2305.10645/) (2023)
- [LLM-Driven Feedback for Enhancing Conceptual Design Learning in Database Systems Courses](https://mlsanity.com/paper/2412.17892/) (2024)

## Abstract (arXiv)

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.