Open access
Sep 2026
From Black-Box Grading to Pedagogically Aligned AI Assessment: A Hybrid LLM–RAG Framework for Explainable and Scalable Automated Code Evaluation
It is demonstrated that reliable AI-assisted assessment emerges from the integration of LLMs within structured and context-aware systems, rather than from model capabilities alone.
Pablo Manuel Vigara Gallego, Ascensión López-Vargas, Ángel García-Beltrán et al.
· Applied Sciences · 0 citations