← Learning
Notes, experiments and open questions from following CMU 11-768: AI Agents (Fall 2026), taught by Graham Neubig and Daniel Fried.
Ground rules. I don't post assignment solution code (the course policy asks students not to). I post experiments, plots and design decisions instead. Any AI help is disclosed in the post.
Assignments & experiments
A1 · Sep 14 A2 · Oct 1 A3 · Oct 29
Training
Project
Research project
Agent Capabilities
L1 · Aug 25 L2 · Aug 27 L3 · Sep 1 Context Management for Long-Context Agents
slides · video L4 · Sep 3 L5 · Sep 8 Planning, Task Decomposition, and Multi-Agent Coordination
slides · video Domains
L6 · Sep 10 L7 · Sep 15 L10 · Sep 24 Deep Research Agents (Akari Asai)
slides Training
L8 · Sep 17 Supervised Fine-Tuning (SFT) (Yueqi Song)
slides · video L9 · Sep 22 L11 · Sep 29
Advanced RL Algorithms
L12 · Oct 1
RL Systems (Apurva Gandhi)
Safety & Frameworks
L13 · Oct 6
Sandboxing and Credential Management
L14 · Oct 8
OpenHands
L15 · Oct 20
LangGraph
L16 · Oct 22
Observability and Monitoring (Eric Wallace)
Interaction & Search
L17 · Oct 27
Agents and the Future of Work (Zora Wang)
L18 · Oct 29
Multi-Agent Interaction (Saujas Vaduguru)
L19 · Nov 10
Human-Agent Interaction (Valerie Chen)
L20 · Nov 12
Reranking and Critic Models
L21 · Nov 17
Tree Search (JY Koh)
Guest Lectures
L22 · Nov 19
Guest Lecture (Karthik Narasimhan)
L23 · Nov 24
Guest Lecture (Sasha Rush)