Presents techniques for generating rich, formative feedback in automated evaluation of visual diagrammatic languages.
Automated assessment is an essential part of eLearning. Although comparatively easy for multiple choice questions (MCQs), automated assessment is more difficult for complex artifacts such as diagrams or source code. Existing diagrammatic assessment engines often produce binary or non-specific error reports that leave students uncertain about how to fix structural or semantic flaws. This paper introduces an approach to enhance feedback in automated diagram assessment by comparing graph representations of student submissions against reference diagrams, identifying detailed structural discrepancies, and generating incremental, formative hints that guide learners toward correct solutions.
$ rg --related ./research
OASIcs, Volume 145, ICPEC 2026
While Learning Management Systems (LMS) like Moodle are ubiquitous in higher education, they often lack dynamic, personalized academic support. We present GamiBot, an intelligent pedagogical agent natively integrated into Moodle to bridge this gap. GamiBot combines Large Language Model (LLM)…
Schloss Dagstuhl – Leibniz-Zentrum für Informatik
Presents GamiBot, an AI-powered pedagogical agent integrated into Moodle combining conversational RAG assistance, automated feedback, and native gamification mechanics.
Electronics
Automated assessment tools for programming assignments have become increasingly popular in computing education. These tools offer a cost-effective and highly available way to provide timely and consistent feedback to students. However, when evaluating a logically incorrect source code, there are…
If this work intersects with your product, institution, or research program, let’s map the shortest credible route to a working system.
Google Analytics helps me understand aggregate portfolio usage. It will not load unless you accept, and advertising storage stays disabled. You can change this choice at any time.
Read the privacy and storage details