The Embedded AI Designer Framework redefines educators as active co-designers who encode disciplinary reasoning and pedagogical intent directly into GenAI systems. Faculty agency is exercised through a Pedagogy-AI Co-evolution Loop consisting of intentional design, orchestrated mediation, and reflective alignment.

This paper identifies a critical “agreeableness bias” where LLM judges excel at identifying valid outputs but fail significantly at spotting invalid ones. To solve this, the authors propose a “minority-veto” strategy and a regression-based framework to ensure more accurate and reliable AI evaluations.

This paper presents a conceptual framework for using GenAI to simulate realistic professional workplace interactions, bridging the gap between academic instruction and practical competency-based education. By leveraging LLMs to mimic human behavior, the framework provides a cost-effective, scalable solution for immersive role-playing across various disciplines.

This study explores a hybrid model where human Teaching Assistants (TAs) review and modify AI-generated feedback for programming exercises. While students perceived an improvement in feedback quality, the hybrid approach did not consistently lead to better student performance and revealed risks of TA complacency.

This research demonstrates that while GPT-4 outperforms traditional Automated Program Repair (APR) tools in generating code fixes, it still suffers from significant failure rates in bug detection and hallucination. The authors propose a new architecture that combines LLMs with an evaluation oracle to achieve near-perfect bug detection and high-quality feedback.

This paper proposes a fully automated framework that generates program repairs for incorrect student assignments in real-time. By re-factoring existing correct solutions into various semantically equivalent forms, the system can precisely match a student’s buggy code to the closest correct structure and suggest minimal, accurate fixes.