Admission requirements
Admission requirements
Assumed prior knowledge:
Elementary calculus and linear algebra; basics of machine learning. Ability to program in Python. Previous experience with LLMs is strongly encouraged.
This course is open to students of the Master Programs Computer Science (AI-track only) and Creative Intelligence and Technology. (Other Computer Science tracks, please switch to the AI track before we can admit you.)
Description
Agentic LLMs are Large Language Models (LLMs) that (1) reason, (2) act, and (3) interact. After an introduction to modern LLM architectures and training procedures, the course is organized into three categories.
The research in the first category covers reasoning, reflection, and retrieval, aiming to improve decision making; the second category covers action models, robots, and tools, aiming for agents that act as useful assistants; the third category focuses on multi-agent systems, aiming for collaborative task solving and simulating interaction to study emergent social behavior.
Throughout the course, we discuss applications of agentic LLMs, for instance, in medical diagnosis, logistics and financial market analysis. Meanwhile, self-reflective agents playing roles and interacting with one another augment the process of scientific research itself. Further, agentic LLMs address the problem of LLMs running out of training data: inference-time behavior generates new training states, enabling LLMs to keep learning without ever needing larger datasets. We also note that there is a risk associated with LLM assistants taking action in the real world, while agentic LLMs are also likely to benefit society.
Course objectives
After this course, students are able to:
Understand the capabilities of Agentic LLM.
They understand how language models are trained, and how reasoning and self-reflection work in LLMs.
They know how to create an agentic LLM for medical diagnostics.
They are able to setup a simulation of emergent social behavior.
Schedule
The most recent timetable can be found at the Computer Science (MSc) student website.
In MyTimetable; you can find all course and programme schedules; allowing you to create your personal timetable. Activities for which you have enrolled via MyStudyMap will automatically appear in your timetable.
Additionally; you can easily link MyTimetable to a calendar app on your phone; and schedule changes will be automatically updated in your calendar. You can also choose to receive email notifications about schedule changes. You can enable notifications in Settings after logging in.
Questions? Watch the video; read the instructions; or contact the ISSC helpdesk.
Note: Joint Degree students from Leiden/Delft need to combine information from both the Leiden and Delft MyTimetables to see a complete schedule. This video explains how to do it.
Teaching method
The course consists of weekly lectures and programming assignments (in Python).
Total hours of study 6 EC course: 168 hrs.
Assesment method
The final grade will be the average of grades for practical assignments (100%).
All assignments are weighed equally.
The teacher will inform the students how the inspection and follow-up discussion of the assignment grading will take place.
Resit, review & feedback
A resit opportunity will be offered for a limited number of assignments. Details are explained in the lectures and on Brightspace.
As a student, you are responsible for enrolling on time through MyStudyMap.
Reading list
Mandatory book: Agentic LLM, van der Meer, van Duijn, Plaat, and van Stein, 2026. Freely available and provided in the course.
Registration
As a student; you are responsible for enrolling on time through MyStudyMap.
In this short video; you can see step-by-step how to enrol for courses in MyStudyMap.
Extensive information about the operation of MyStudyMap can be found here.
There are two enrolment periods per year:
Enrolment for the fall opens in July
Enrolment for the spring opens in December
See this page for more information about deadlines and enrolling for courses and exams.
Note:
It is mandatory to enrol for all activities of a course that you are going to follow.
Your enrolment is only complete when you submit your course planning in the ‘Ready for enrolment’ tab by clicking ‘Send’.
Contact
Lecturers: Michiel van der Meer, Aske Plaat, Niki van Stein, Max van Duijn
Email: agenticllms@liacs.leidenuniv.nl
Remarks
This course is an elective course for the Master Computer Science (available only for AI track students) and for the Master Creative Intelligence and Technology