AI-Supported Update Pipeline for Continuously Evolving Learning Content in Information Management

Thesis (BA/MA/GR)

Advisor(s): Alisa Mehler (alisa.mehler(at)tum.de)

CONTEXT

Knowledge in the field of Information Management evolves rapidly: new technologies, emerging governance practices, and continuous academic contributions quickly make static learning resources outdated. Traditional textbooks provide foundational structure, but they inherently lack mechanisms for continuous renewal.

Large Language Models (LLMs) enable new approaches to keep learning systems dynamic by integrating external sources such as research papers, industry reports, and white papers into existing learning modules.

This thesis explores how an AI-supported update pipeline can be designed and implemented to systematically discover, evaluate, and integrate new knowledge into an LLM-based personalized learning system based on the textbook Informationsmanagement by Krcmar (2015).

The objective is to build a prototype lifecycle that ensures learning content remains current, relevant, and aligned with the textbook’s modular structure, transforming the system into a sustainable alternative to static educational material. This thesis contributes to the long-term viability and practical relevance of LLM-driven learning journeys.

EXEMPLARY FEATURES

• Definition of specialized agent roles (generation, review, QA, governance)
• Multi-stage validation workflows (Generate–Verify–Refine)
• Prompt governance mechanisms and quality criteria
• Comparison of single-agent vs. multi-agent architectures

• Human-in-the-loop integration for critical learning content

   

EXEMPLARY QUESTIONS

The topic can be approached through guiding research questions such as:

• What sources can be used to continuously enhance learning content in rapidly evolving domains?
• How can relevance and consistency of newly integrated knowledge be ensured automatically?
• Which mechanisms encourage learners to engage with updated or extended content?
• What risks emerge when educational material is dynamically updated through LLMs, and how can they be mitigated?
• How can lifecycle management approaches prevent learning systems from becoming obsolete?

These and similar questions can serve as a foundation for a student thesis (BA/MA/Guided Research).

 

TASK(S)

• Review literature on dynamic learning content and lifecycle management
• Design an update pipeline (discovery–evaluation–integration–versioning)
• Develop LLM-based mechanisms for relevance and contradiction checking
• Implement a prototype aligned with modular textbook content

• Discuss challenges such as bias, overload, and maintainability

   

REQUIREMENTS

• High autonomy and structured work style
• Strong interest in AI, Information Systems, and digital learning
• Experience with Python and prototypical development
• Motivation for scientific evaluation and applied research

• Structured, reliable & self-motivated work style

   

FURTHER INFORMATION

The thesis can be written in English or German. The topic can also be adapted to your interests. If you have further questions, please do not hesitate to contact us directly. Please send your application including our specific application form, a current transcript of records and your CV to alisa.mehler(at)tum.de. Please also note that we can only consider applications with complete documents.