Andrej Košir

Janez Perš, Jon Muhovič, Andrej Košir et al.

Handwritten STEM exams capture open-ended reasoning and diagrams, but manual grading is slow and difficult to scale. We present an end-to-end workflow for grading scanned handwritten engineering quizzes with multimodal large language models (LLMs) that preserves the standard exam process (A4 paper, unconstrained student handwriting). The lecturer provides only a handwritten reference solution (100%) and a short set of grading rules; the reference is converted into a text-only summary that conditions grading without exposing the reference scan. Reliability is achieved through a multi-stage design with a format/presence check to prevent grading blank answers, an ensemble of independent graders, supervisor aggregation, and rigid templates with deterministic validation to produce auditable, machine-parseable reports. We evaluate the frozen pipeline in a clean-room protocol on a held-out real course quiz in Slovenian, including hand-drawn circuit schematics. With state-of-the-art backends (GPT-5.2 and Gemini-3 Pro), the full pipeline achieves $\approx$8-point mean absolute difference to lecturer grades with low bias and an estimated manual-review trigger rate of $\approx$17% at $D_{\max}=40$. Ablations show that trivial prompting and removing the reference solution substantially degrade accuracy and introduce systematic over-grading, confirming that structured prompting and reference grounding are essential.

A. Fuster-López, J. M. Cruz, P. Guerrero-García et al.

The use of e-learning systems has a long tradition, where students can study online helped by a system. In this context, the use of recommender systems is relatively new. In our research project, we investigated various ways to create a recommender system. They all aim at facilitating the learning and understanding of a student. We present a common concept of the learning path and its learning indicators and embed 5 different recommenders in this context.