Large Language Models and Agents (FSS2026)

Large language models (LLMs) such as ChatGPT, Claude, Llama, Gemini, and Mistral have the potential to enable a wide range of new applications and to significantly improve the performance of existing systems. The course introduces students to LLMs and LLM agents and teaches them how to employ language models and LLM agents within different applications.

The course covers the following topics:

1. Introduction to LLMs
2. Prompt engineering
3. LLM-based agents
4. Tool use and environment interaction
5. Retrieval augmented generation
6. Context engineering for LLM agents
7. Safety and security of LLM agents
8. Evaluation of LLM agents

The course participants gain knowledge about the principles of training LLMs. They will be able to identify opportunities for employing LLMs in business applications and will learn to apply prompt engineering techniques as well as agent frameworks for solving complex tasks. In the second half of the course, the participants apply their knowledge in team projects and will report about the results of the projects in the form of a written report as well as an oral presentation.

Due to high demand, this course will again be offered in FSS2026. The course will be extended to a 6 ECTS course consisting of two parts: A theory part consisting of a lecture and an exam (3 ECTS, IE685) and a project part (3ECTS, IE686) in which student teams implement and evaluate  LLM agents for specific use cases.

• Tuesday, 10:15–11:45. Location B6, A101 (Starting: 10.02.2026)
• Wednesday, 12:00–13:30. Location: B6, A101 

• Dr. Ralph Peeters
• Prof. Dr. Christian Bizer
• Aaron Steiner

In the second half of the course, students will work on applied projects in teams. The grade received for this part of the course is based on the quality of the contents of their project report (50%) and the associated presentation and Q&A (50%). 

• IE685: 3 ECTS: Final exam
• IE686: 3 ECTS: 50 % project report, 50 % presentation and Q&A

• Programming skills in Python
• Basic machine learning concepts and techniques

• The course is open to students of the Mannheim Master in Data Science, the Mannheim Master in Social Data Science, and Master Business Informatics.
• The course is restricted to 50 participants. The registration for the course is organized by the Studiengang Management and is done via Portal2. 

• LangChain
• Tavily

1. Zhao, et al.: A Survey of Large Language Models, arXiv:2303.18223, 2024.
2. Wang, et al.: A Survey on Large Language Model Based Autonomous Agents. Frontiers of Computer Science, 2024.
3. Mohammadi, et al.: Evaluation and benchmarking of LLM agents: A survey. SIGKDD Conference on Knowledge Discovery and Data Mining, 2025.
4. Wang, et al.: A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment. arXiv:2504.15585, 2025.
5. Zhou, et al.: A Comprehensive Survey on Pretrained Foundation Models: A History from BERT to ChatGPT, 2024, International Journal of Machine Learning and Cybernetics.