Theses

Large language models allow to support human learning and work in real time. This joint activity has potential to both positively and negatively impact human cognition and problem solving. The project aims to build a student-facing prototype for analytics that reflect their interaction with LLMs when they learn. The prototype will mirror to the individuals how they use an LLM application, when they rely on it during learning, and whether that supports their intended goals for learning.

Communication on Artemis already provides context-sensitive interactions between students and instructors. In this thesis, communication should be enhanced based on new functionality. The user experience should be further enhanced so that it makes more fun and is comparable to platforms such as Slack and Discord. This can include the enhancements of the new mobile Artemis apps for iOS and Android. Artemis is open source and available on https://github.com/ls1intum/Artemis

Apollon is an online modeling editor written in React. It offers an easy to use and lightweight experience to learn UML and other notations in an interactive environment. It runs as standalone version on https://apollon.ase.in.tum.de offering a collaborative modeling experience without accounts. It is also integrated into Artemis to enable modeling exercises. Students create models, tutors assess those models and provide feedback which students can then see in order to improve their modeling skills.

Programming exercises in Artemis can be realized with Bitbucket/Bamboo, Gitlab/Jenkins, GitlabCI or LocalVCS/CI. This allows flexibility for Artemis admins. LocalVCS/CI provides an easy setup for developers and for universities to try out Artemis. However, not all functionality for programming exercises is available on all combinations of version control and continuous integration subsystems In this thesis, the missing features should be implemented. In addition, the concept of build agents and dockerized builds should be realized within LocalCI.

Artemis supports local VCS and CI using Docker containers. This provides many benefits like better performance, easier setup and reduce maintenance effort. However, the implementation is still preliminary and some features of programming exercises are missing. In this thesis, you extend the capabilities and implement a more flexible solution for CI taking scalability with build agents and customizable build plans into account. Artemis is open source and available on https://github.com/ls1intum/Artemis

Students can struggle with exercises. Then, it would be helpful if Artemis would provide help pro-actively, e.g. by using generative AI (ChatGPT). In this thesis, you extend Artemis so that student receive automatic and pro-active help when they struggle. In an evaluation, you would determine the usefulness of the approach and assess the effects on the learning experience. Artemis is open source and available on https://github.com/ls1intum/Artemis

Artemis supports any programming language for programming exercises. Currently, it includes templates for many popular languages, however templates for a couple of languages is still missing. In this thesis, new templates for programming exercises will be developed and tested with the Bitbucket/Bamboo and Gitlab/Jenkins and LocalVCS/CI. In addition, static code analysis should be integrated into more programming exercise templates. Artemis is open source and available on https://github.com/ls1intum/Artemis

Abstract TBA

TBA

This thesis will focus on the integration of AL into Artemis. We will use theoretical research and a requirements analysis to create a software design based on the existing architecture of Artemis. The proposed design will be implemented in the LMS. Finally, the thesis will document the analysis of the current state, the requirements engineering process, and the development of the features proposed in this section. Artemis is open source and available on https://github.

Abstract TBA

In the evolving landscape of computer science education, the burgeoning student population necessitates a shift from traditional teaching paradigms. The Artemis teaching platform, with its interactive learning approach, offers a scalable solution for large courses. However, a notable challenge remains: the uniform distribution of programming exercises, regardless of individual student proficiency. Recognizing the diverse skill set and learning needs of students, this master thesis proposes a transformative solution — the utilization of Generative Pre-trained Transformer models, particularly Large Language Models (LLM), for adaptive programming exercise generation.

Online educational platforms, including Coursera, Udacity, edX, and Khan Academy, offer diverse courses and rely heavily on exercises to reinforce learning. Among these, the Artemis platform from the Technical University of Munich has introduced specialized programming exercises. However, a pressing challenge is the time and effort instructors invest in creating these exercises. This bachelor thesis, supervised by Prof. Dr. Stephan Krusche and advised by Patrick Bassner, M.Sc., proposes the integration of OpenAI’s GPT-4 into Artemis to assist instructors in generating programming exercises.

With the high prevalence of mobile devices among students, a significant need exists to adapt and optimize the web-based Unified Modeling Language (UML) modeling tool, Apollon, for mobile devices. Artemis, a learning platform integrating Apollon, has multiple related iOS apps also seeking an Apollon integration. This thesis aims to bridge this usability gap, making UML modeling more efficient and user-friendly within the Artemis app ecosystem. The objectives include developing a Swift package for Apollon, integrating it into Themis for efficient feedback and grading, and incorporating it into Artemis for iOS to allow students to model from their mobile devices.