arXiv：cs.AI（全量分类）· Sara Riazi, Pedram Rooshenas·· 5 小时前AI 评分31
教育者引导的 LLM 教学智能体：概念数据库设计中的脚手架式反馈
An Educator-Guided LLM Pedagogical Agent for Scaffolded Feedback in Conceptual Database Design
AI 导读
研究者提出一种教育者引导的 LLM 教学智能体，集成于 ERD 编辑器，基于学生作品、作业要求、教师评分标准和教学资源生成脚手架式反馈，架构将隐藏的诊断与面向学生的反馈流程分离。系统采用四阶段工作流，每次反馈请求生成与版本化 ERD 状态关联的有状态 episode。在三个 ERD 环境、383 个反馈 episode 的部署中，71.1% 的目标级修改完全或部分采纳了隐藏诊断目标。
正文
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.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.00870 [cs.AI] |
| (or arXiv:2610.00870v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.00870 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Pedram Rooshenas [view email]
[v1]
Thu, 1 Oct 2026 00:38:50 UTC (2,433 KB)
来源：arXiv：cs.AI（全量分类） · arxiv.org