Theses

If you are interested in writing your thesis in the research group, apply using the

Important: Please do not email individual team members, they will not respond to your email!

Open

Master's ThesesAdvanced LLM Techniques for Text-Based Exercises in Higher Education
Year2024
Advisor(s)Felix T.J. Dietrich
Supervisor(s)Prof. Dr. Stephan Krusche
Abstract

This master’s thesis aims to enhance educational outcomes on Artemis by reducing tutor workload and improving the student learning experience. We’ll build on Athena’s preliminary work that deployed Large Language Models (LLMs) like GPT-4 to provide automatic feedback on text-based exercises. The focus is to employ more advanced LLM techniques such as Retrieval Augmented Generation (RAG) and fine-tuning Llama 3 with historical feedback data. The project will proceed in two phases: refining the feedback system for more context-sensitive, automated responses, and then evaluating and comparing the system’s accuracy, efficiency, and educational impact.

Master's ThesesImplementing an AI-Driven Chatbot in CIT: Enhancing Information Accessibility and Administrative Efficiency
Year2024
Advisor(s)Prof. Dr. Stephan Krusche
Abstract

The CIT school at TUM faces a significant challenge in managing the high volume of routine inquiries from students and faculty, which currently are handled primarily through traditional communication channels such as emails. This results in an administrative burden that could be alleviated through automated processes. This thesis outlines the development of a chatbot designed to autonomously handle common inquiries, directing users to appropriate resources and thereby enhancing the efficiency of service delivery within CIT.

Master's ThesesOptimizing Module Management in CIT: A Framework for Enhanced Coordination and Efficiency
Year2024
Advisor(s)Prof. Dr. Stephan Krusche
Abstract

The current structure of module management within the school CIT features an overlapping array of responsibilities among coordinators that spans multiple departments and competence centers. This structure results in inefficiencies and confusion due to the lack of a cohesive framework, impacting the strategic alignment of educational objectives and research initiatives. This thesis proposes a redefined framework aimed at streamlining module coordination, which will establish clear roles and minimize content overlap, aligning modules with CIT’s broader educational and research goals.

Master's ThesesPrototyping learning analytics for human-AI interaction
Year2023
Advisor(s)Prof. Dr. Stephan Krusche, and Prof. Dr. Oleksandra Poquet
Abstract

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.

Master's ThesesCommunication in Artemis
Year2023
Advisor(s)Prof. Dr. Stephan Krusche
Abstract

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

Master's ThesesFurther Development of Apollon
Year2023
Advisor(s)Prof. Dr. Stephan Krusche
Abstract

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.

Master's ThesesFurther Development of the Version Control and Continuous Integration in Artemis
Year2023
Advisor(s)Prof. Dr. Stephan Krusche
Abstract

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.

Master's ThesesLocal Continuous Integration in Artemis
Year2023
Advisor(s)Prof. Dr. Stephan Krusche
Abstract

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

Bachelor's ThesesTemplates for All Programming Languages in Artemis
Year2023
Advisor(s)Prof. Dr. Stephan Krusche
Abstract

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

In Progress

Master's ThesesImproving Adaptive Learning in an Interactive Teaching Platform
Start DateNovember 2023
Advisor(s)Maximilian Anzinger
Supervisor(s)Prof. Dr. Stephan Krusche
StudentRaphael Stief
Abstract

Research suggests that learning paths might positively impact students’ academic success. Artemis also recently introduced learning paths, however, they are rarely used due to the creation process being time-consuming and having poor usability. In this thesis, we will add improvements to the creation and import processes of competencies, which are the basis for learning paths. To achieve this, we will conduct user interviews with instructors, identifying the changes providing the largest benefit and implementing those.

Master's ThesesSemi-Automatic Feedback Generation for Programming Exercises
Start DateJanuary 2024
Advisor(s)Maximilian Sölch
Supervisor(s)Prof. Dr. Stephan Krusche
StudentMarlon Bucciarelli
Abstract

The number of computer science students is rising significantly each semester. To meet the demand for prompt and effective feedback, particularly in programming tasks, it is essential to enhance Athena, a platform for (semi-)automated text and programming assessments, to facilitate a higher volume of (semi-)automated feedback. This thesis aims to develop and integrate two new modules into Athena, evaluating them based on resource consumption, including computational capacity and memory usage, and the relevance of their feedback to specific programming tasks.

Bachelor's ThesesIncorporating Lecture Content into IRIS
Start DateJanuary 2024
Advisor(s)Patrick Bassner
Supervisor(s)Prof. Dr. Stephan Krusche
StudentYassine Souissi
Abstract

In this thesis, the goal is to enhance the contextual awareness of a GPT-based educational chatbot, named IRIS, on the Artemis Learning Platform by incorporating lecture content. To do this, the lecture slides should be embedded into a vector database, and the chatbot should be able to retrieve the most relevant slides based on the user’s query in order to provide the most relevant answer. Artemis is open source and available on https://github.

Master's ThesesLeveraging Large Language Models for Proactive Assistance in Artemis
Start DateJanuary 2024
Advisor(s)Patrick Bassner
Supervisor(s)Prof. Dr. Stephan Krusche
StudentYılmaz Kaan Çaylı
Abstract

The challenges encountered by students during the completion of exercises necessitate the implementation of a proactive assistance mechanism within Artemis. This could potentially be achieved through the integration of generative AI technologies such as ChatGPT. The objective of this thesis is to augment Artemis with the capability to provide automatic and proactive assistance to students when they encounter difficulties. The effectiveness and impact of this approach on the learning experience will be evaluated through a comprehensive assessment.

Master's ThesesDynamic Lecture Content Management in Artemis
Start DateFebruary 2024
Advisor(s)Patrick Bassner
Supervisor(s)Prof. Dr. Stephan Krusche
StudentAybike Ece Eren
Abstract

The thesis aims to enhance the instructor interface and student experience in the IRIS learning platform. The project will introduce a thumbnail grid for instructors to manage slides intuitively, ensuring persistent configurations even when slides are updated. The system will adapt to changes, such as the addition of new slides, by automatically adjusting the selection and maintaining the overall structure. Advanced features like automatic slide number extraction and adaptive reference management will be implemented to maintain continuity when slides are updated.

Bachelor's ThesesTease 2 0 Enhancing Matching Effectiveness and Usability for Team Allocation in Project Courses
Start DateFebruary 2024
Advisor(s)Ramona Beinstingel, and Matthias Linhuber
Supervisor(s)Prof. Dr. Stephan Krusche
StudentPhilipp Nagy
Abstract

This thesis contributes to the enhancement of the Team Allocator for Software Engineering courses, an open-source tool for forming student teams. The focus is on optimizing data import and export functionalities, refining the matching algorithm, improving the user interface and experience, and implementing a serverside component to enable synchronous multi-user collaboration. The methodology employed is agile development with 2-3 week product increments, allowing for regular testing and release cycles. The main contribution of this work lies in providing significant upgrades to the TEASE project, enhancing its usability and efficiency in project-based educational settings.

Master's ThesesEvaluation of a GPT-based Chatbot for Higher Education
Start DateMarch 2024
Advisor(s)Patrick Bassner
Supervisor(s)Prof. Dr. Stephan Krusche
StudentAnna Lottner
Abstract

The goal of this thesis is to evaluate the effectiveness of IRIS, a GPT-based chatbot for higher education. The chatbot is integrated into the Artemis learning platform and is designed to provide assistance to students when they encounter difficulties. In addition, the chatbot is capable of answering questions related to the course content. Instructors can benefit from IRIS through assistance in exercise generation. In this thesis, the effectiveness of IRIS will be evaluated through a combination of quantitative and qualitative methods.

Bachelor's ThesesCommunication Enhancement For Improved Learning in Artemis
Start DateApril 2024
Advisor(s)Ramona Beinstingel
Supervisor(s)Prof. Dr. Stephan Krusche
StudentEge Kurt
Abstract

This thesis proposal addresses communication challenges in Artemis. The aim is to enhance Artemis by introducing a refined communication module. The identified problems include duplication in communication sections, ab- sence of document-sharing, and limitations in threaded conversations. Moti- vated by the need for a robust communication platform, this thesis proposal suggests improvements guided by Nielsen’s Heuristics. Key objectives involve a unified messaging system, enhanced message thread functionality, collabo- rative document sharing, and improved UI design.

Bachelor's ThesesVisualization of Endpoint-Connections
Start DateApril 2024
Advisor(s)Markus Paulsen, and Maximilian Anzinger
Supervisor(s)Prof. Dr. Stephan Krusche
StudentJan Thurner
Abstract

Getting an overview of different REST calls and the respective endpoints of large software systems is a tedious and error-prone task, as there are many endpoints, and the generation of URIs is often profoundly nested. Faulty endpoints may lead to decreased usability of a system. Manually analyzing the client- and server-sided authorization steps is equally tedious, as it happens in many places. Faulty authorization may have severe consequences. This thesis describes the development of a GitHub action analyzing client-sided REST calls and the respective server-sided REST endpoints, the used URLs, and the client- and server-sided authorization.

Master's ThesesEnhancing Learning Path Usability in Artemis Through Intuitive User Interface Design
Start DateApril 2024
Advisor(s)Maximilian Anzinger, and Ramona Beinstingel
Supervisor(s)Prof. Dr. Stephan Krusche
StudentJohannes Wiest
Abstract

The rapid evolution of information and communication technologies led to widespread adoption of E-learning systems, particularly during the pandemic when traditional in-person education was not possible. This shift underlined the importance of diverse learning rhythms and paces among students, a challenge particularly in larger classes. To address this, Artemis, an open-source interactive learning platform, introduced learning paths tailored to individual learner goals and capacities. However, despite the functionality of learning paths, Artemis currently lacks an intuitive user interface, hindering the adoption and usability of the feature.

Master's ThesesEvolving LLM-Based Feedback in Programming Education
Start DateApril 2024
Advisor(s)Maximilian Sölch
Supervisor(s)Prof. Dr. Stephan Krusche
StudentDmytro Polityka
Abstract

This master’s thesis aims to refine an LLM-based feedback system for program- ming assignments in the Artemis Learning Management System. Despite previous advancements, challenges remain in providing accurate, adaptive, and scalable feedback. The proposed enhancements include the integration of model vector databases, specialized models like Code Llama 2, and an agentic-based approach to address issues of language compatibility and feedback precision. The objective is to reduce manual workload for educators and provide immediate, tailored feed- back to students, thereby enhancing the educational experience and efficiency in learning programming skills.

Bachelor's ThesesTowards on Premises Kubernetes Deployments: Storage and User Management
Start DateMay 2024
Advisor(s)Matthias Linhuber, and Robert Jandow
Supervisor(s)Prof. Dr. Stephan Krusche
StudentColin Wilk
Abstract

The emergence of Kubernetes has transformed the practices surrounding the deployment and management of containerized applications by introducing advanced automation, scalability, and operational ease. This thesis focuses on enhancing the Kubernetes deployment at the Technical University of Munich. We identify key issues within the current deployment architecture, including the lack of persistent storage in the Kubernetes cluster, making it unsuitable for stateful applications like Artemis, the cumbersome quality assurance workflow for Artemis, and lacking access control hindering educational use of the Kubernetes cluster.

Bachelor's ThesesUI/UX Improvement of the Artemis Student View
Start DateMay 2024
Advisor(s)Ramona Beinstingel
Supervisor(s)Prof. Dr. Stephan Krusche
StudentEge Dogu Kaya
Abstract

Artemis is an online learning platform that offers students and instructors a wide range of interactive learning experiences. However, the platform contains design inconsistencies as well as confusing and complex layout elements in the exam mode, course overview and tutorial groups from the student’s point of view. As a result, the complexity and distractiveness of the layouts hamper the user ex- perience, making it difficult for students to navigate and utilize the platform ef- fectively.

Master's ThesesEnhancing Learning Path Recommendations in Artemis Through Repeated Tests
Start DateMay 2024
Advisor(s)Maximilian Anzinger
Supervisor(s)Prof. Dr. Stephan Krusche
StudentJohannes Stöhr
Abstract

Artemis is a learning management platform that offers students different exercise types as well as lecture materials. To help students navigate the exercises and lectures Artemis offers learning paths and makes suggestions about the order of the resources. This thesis aims to optimize the learning path recommendations within Artemis by integrating repeated testing and improving the accuracy and transparency of progress metrics. The expected outcome is a more efficient and engaging learning experience for students, with personalized suggestions that adapt to their learning pace and needs.

Master's ThesesInclusive Learning Environments in the Cloud: Scalable Online IDEs for Higher Education
Start DateJune 2024
Advisor(s)Matthias Linhuber
Supervisor(s)Prof. Dr. Stephan Krusche
StudentYannik Schmidt
Abstract

The interactive learning platform Artemis offers students a unique opportunity to learn and train software engineering skills online. Especially for advanced courses and topics, students need to set up a local integrated development environment (IDE) to work on their exercises which can be a daunting task. The main objectives of the thesis include the integration of the customized online IDE Theia within Artemis and the setup of a performant execution environment on Kubernetes.

Finished

StudentAdvisor(s)Supervisor(s)TitleTypeYear
Jonathan OstertagRamona BeinstingelProf. Dr. Stephan KruscheImprovement of the General Artemis User ExperienceBachelor's Theses10/2023 - 03/2024
Basak AkanMatthias LinhuberProf. Dr. Stephan KruscheLTI Based Artemis Integration in Learning Management SystemsMaster's Theses08/2023 - 02/2024
Andreas ReschMatthias Linhuber, and Robert JandowProf. Dr. Stephan KruscheA Domain Specific Language for Streamlining CI Job Configuration for Programming ExercisesMaster's Theses08/2023 - 02/2024
Alexander GörtzenMaximilian SölchProf. Dr. Stephan KruscheDesign Anywhere: UML Modeling on Mobile DevicesBachelor's Theses09/2023 - 02/2024
Xinyao LiuPatrick BassnerProf. Dr. Stephan KruscheLeveraging Generative AI for Adaptive Exercise GenerationMaster's Theses08/2023 - 02/2024
Michael DyerPatrick BassnerProf. Dr. Stephan KruscheLeveraging Large Language Models for Assisted Programming Exercise GenerationBachelor's Theses08/2023 - 01/2024
Maximilian AnzingerPatrick BassnerProf. Dr. Stephan KruscheIntegration of Adaptive Learning in Interactive Online Learning EnvironmentsMaster's Theses05/2023 - 10/2023
Benedikt GeisbergerPatrick Bassner, and Matthias LinhuberProf. Dr. Stephan KruscheUser-Centered Design in Agile University ProjectsBachelor's Theses05/2023 - 10/2023
Tarlan IsmayilsoyMaximilian SölchProf. Dr. Stephan KruscheImproved Assessment Workflow of Exercises on Mobile DevicesMaster's Theses04/2023 - 10/2023
Valeryia AndraichukMatthias Linhuber, and Philipp ZagarProf. Dr. Stephan KruschePROMPT - Process Model for Managing Project-Based TeachingMaster's Theses03/2023 - 09/2023
Felix DietrichMaximilian SölchProf. Dr. Stephan KruscheLeveraging LLMs for Automated Feedback Generation on ExercisesMaster's Theses03/2023 - 09/2023
Paul SchwindMaximilian SölchProf. Dr. Stephan KruscheGeneralizing Machine-Learning Based AssessmentsMaster's Theses03/2023 - 09/2023
Stefanie MangerMaximilian SölchProf. Dr. Stephan KruscheEvaluating and Optimizing the iPraktikum’s intro courseBachelor's Theses03/2023 - 07/2023
Adrian SohnMatthias Linhuber, and Christoph WeinhuberProf. Dr. Stephan KruscheExtending TEASE Enhancing the Reference Implementation of TEMPOBachelor's Theses02/2023 - 06/2023
Florian GareisMatthias LinhuberProf. Dr. Stephan KruscheCode Quality Assurance Using E2E TestsMaster's Theses12/2022 - 06/2023
Ludwig PuslMatthias LinhuberProf. Dr. Stephan KruscheAutomatic Test Environment Deployment and Continuous Security Analysis for Learning PlatformsMaster's Theses09/2022 - 06/2023
Timothy SummersPhilipp ZagarOptimising the User Experience and Design of the iOS TUM Campus AppBachelor's Theses12/2022 - 05/2023
Anton WyrowskiPhilipp ZagarPrivacy-Friendly Notifications for the iOS TUM Campus AppBachelor's Theses12/2022 - 04/2023
David LinPhilipp ZagarGlobal User-Centric In-App Search for the iOS TUM Campus AppBachelor's Theses11/2022 - 03/2023
Simon LeißMatthias LinhuberProf. Dr. Stephan KruscheScaling of a monolith application using microservice architectureMaster's Theses07/2022 - 01/2023
Manuel MansoMaximilian SölchProf. Dr. Stephan KruscheExtension of LTI Support in ArtemisMaster's Theses06/2022 - 12/2022
Benjamin Sebastian SchmitzDr. Jan Philip Bernius, and Matthias LinhuberProf. Dr. Stephan KruscheAutomatic Correction of Programming Exercises With Artemis and Gitlab CiSeminar's Theses01/2022 - 12/2022
Moritz AberleMaximilian SölchProf. Dr. Stephan KruscheAdaptive Learning in an Interactive Teaching PlatformMaster's Theses05/2022 - 11/2022
Robyn KöllePhilipp Zagar, and Maximilian SölchProf. Dr. Stephan KruscheImplementing Context-Sensitive Widget Recommendations into the TUM Campus AppBachelor's Theses06/2022 - 10/2022
Svilen KirovPhilipp ZagarPrivacy First: An Open Source Framework for Observability in Modern ApplicationsBachelor's Theses04/2022 - 08/2022
Kilian WarmuthMatthias Linhuber, and Robert JandowProf. Dr. Stephan KruscheTowards a Declarative Definition of Network Configurations Custom Terraform Provider for Rest ApisBachelor's Theses01/2022 - 05/2022
Merlin MehmedEvgeny Volynsky, and Prof. Dr. Stephan KruscheMigration of Artemis Architecture From Monolithic to MicroservicesMaster's Theses06/2021 - 12/2021
Simon LeißProf. Dr. Stephan KruscheProf. Dr. Bernd BrüggeSecuring and Scaling Artemis Websocket ArchitectureBachelor's Theses06/2022 - 11/2021
Lorena SchlesingerProf. Dr. Stephan KruscheProf. Dr. Bernd BrüggeMetis: Multiplying Engagement Through Interacting Socially on the Artemis Learning PlatformMaster's Theses06/2021 - 11/2021
Dominik FuchsProf. Dr. Stephan KruscheProf. Dr. Bernd BrüggeTeaching Analytics in ArtemisBachelor's Theses10/2020 - 04/2021
Stefan WaldhauserProf. Dr. Stephan KruscheProf. Dr. Bernd BrüggeIntegration Learning Analytics in ArtemisBachelor's Theses09/2020 - 03/2021
Philipp BauchProf. Dr. Stephan KruscheProf. Dr. Bernd BrüggeImproved Integration of Plagiarism Detection Into ArtemisBachelor's Theses08/2020 - 02/2021
Martin DunkerProf. Dr. Stephan KruscheProf. Dr. Bernd BrüggeDevelopment of Manual Assessment for Programming Exercises in the Orion PluginBachelor's Theses02/2020 - 08/2020

Head of Research Group



Prof. Dr. Stephan Krusche

Administrative office


Sophia Adelmeier
adelmeie@cit.tum.de

Office: 01.07.052
Phone: +49 (89) 289-18206
Fax: +49 (89) 289-18207 Boltzmannstraße 3
85748 Garching b. München