STML 2026 — LLM Agents
Special Topics in Machine Learning · Graduate course · 15 weeks
The course in one sentence
You will learn how LLM agents work by building one, piece by piece, for 15 weeks — and by reading the papers that invented each piece. The final deliverable is a research-assistant agent that searches and synthesizes answers over this course’s own paper corpus.
Weekly rhythm (3 hours)
| Block | Time |
|---|---|
| Theory lecture | 30 min |
| Paper presentations ×2 (25 min each) | 50 min |
| Break | 10 min |
| Lab (build-from-scratch notebook) | 80 min |
| Wrap-up · next-week preview | 10 min |
15-week map
Ordering principle: concept dependency — every week is understandable using only what came before it.
| Wk | Topic | Wk | Topic |
|---|---|---|---|
| 1 | Course intro · What is an agent? | 9 | Context engineering · Memory |
| 2 | Prompting & reasoning | 10 | Multi-agent + LangGraph + MCP |
| 3 | Reasoning models & RL | 11 | Inference economics |
| 4 | Tool use | 12 | Evaluation & benchmarks |
| 5 | The agent loop (ReAct) | 13 | Trust & security · retrospective |
| 6 | Retrieval augmentation (RAG) | 14 | Final presentations (full day) |
| 7 | Planning & search · Self-reflection | 15 | Final exam (written) |
| 8 | Midterm exam (written) |
Weekly pages are published as the semester progresses.
Before the first class
- Read the API Setup Guide and issue your own API key (or install Ollama). This must be done before the Week 1 lab.
- Bring a laptop with Python 3.10+ available.