Lectures

The lectures are available for download here. We will upload them ahead of the corresponding classes whenever possible. Given the broad and comprehensive topics in this course, we greatly value the shared external resources. We acknowledge and respect the copyrights of publicly available materials, including those from Stanford CS146S Fall 2025, HuggingFace, and other public resources as referenced and noted in the slides. If any oversight has occurred, please do not hesitate to contact Guangjing.

• 

  Overview of Agentic AI Systems
  tl;dr: An Overview of Agentic AI System Principles and Course Syllabus.
  [slides]
  

  Suggested Readings:

  • Agentic AI
• 

  Attention and Transformer
  tl;dr: A Review of Large Language Model Basics.
  [slides]
  

  Suggested Readings:

  • How do Transformers work
  • Attention Is All You Need
  • Attention Is Not All You Need
  • Convolutional Sequence to Sequence Learning
  • Flash Attention
• 

  Large Language Modeling
  tl;dr: An Introduction to Language Modeling and LLM Inference Process.
  [slides]
  

  Suggested Readings:

  • RoPE
  • DeepSeek V3
  • Paged Attention
• 

  Foundation Model and Fine-tuning
  tl;dr: An Introduction to Instruction Tuning and Preference Alignment.
  [slides]
  

  Suggested Readings:

  • Chat Template
  • LoRA
  • DPO
• 

  Context Engineering
  tl;dr: An Introduction to Prompt Design and Context Engineering.
  [slides]
  

  Suggested Readings:

  • Prompting Guide
• 

  Agent Application Basics
  tl;dr: An Introduction to LLM Agent Application Basics.
  [slides]
  

  Suggested Readings:

  • Agents Course
• 

  Agent Tool Design
  tl;dr: An Introduction to Model Context Protocol.
  [slides]
  

  Suggested Readings:

  • Model Context Protocol
  • MCP Tools Beyond API
  • MCP Registry
  • Build a Remote MCP Server
• 

  Agent Memory Design
  tl;dr: An Introduction to AI Agent Memory Design.
  [slides]
  

  Suggested Readings:

  • GenAI Tech Blog
  • Research of Memory in AI
  • Memory in the Age of AI Agents
• 

  Reinforcement Learning Basics
  tl;dr: An Introduction to Reinforcement Learning.
  [slides]
  

  Suggested Readings:

  • HuggingFace RL
• 

  Reinforcement Learning for Agentic AI
  tl;dr: Deep Reinforcement Learning for Agentic AI Design.
  [slides]
  

  Suggested Readings:

  • RLHF
  • Preference Optimization
• 

  Agent Reasoning Basics
  tl;dr: An Introduction to AI Agent Reasoning.
  [slides]
  

  Suggested Readings:

  • CoT
  • Reflexion
  • DeepSeek R1
• 

  AI Agent Planning Design
  tl;dr: An Introduction to AI Agent Planning.
  [slides]
  

  Suggested Readings:

  • AgentGen
  • LaMMA-P
• 

  Multi-Agent System Design
  tl;dr: An Introduction to Multi-Agent Design.
  [slides]
  

  Suggested Readings:

  • HyperAgents
  • Agentic Supernet
  • Why Do Multi-Agent LLM Systems Fail?
• 

  Agentic AI for Security
  tl;dr: An Introduction to Agentic AI for Cybersecurity.
  [slides]
  

  Suggested Readings:

  • LLM4Cybersecurity
• 

  Security of Agentic AI
  tl;dr: An Introduction to Safety and Security of Agentic AI.
  [slides]
  

  Suggested Readings:

  • Agentic AI Safety & Security
  • AI Agents Under Threat
• 

  Agentic AI Evaluation
  tl;dr: An Introduction to Agentic AI Evaluation.
  [slides]
  

  Suggested Readings:

  • LLM Agent Benchmarking Survey
  • LLM as a Judge