Announcement:

Learn more and sign up for the AgentX - AgentBeats Competition here.

Prospective Students

Course Staff

Instructor (Guest) Co-instructor
Dawn Song Xinyun Chen
Dawn Song Xinyun Chen
Professor, UC Berkeley Research Scientist, Meta

Guest Speakers

Yann Dubois
Yann Dubois
Member of Technical Staff
OpenAI
Yangqing Jia
Yangqing Jia
VP, Al System Software
NVIDIA
Jiantao Jiao
Jiantao Jiao
Director of Research & Distinguished Scientist
NVIDIA
Weizhu Chen
Weizhu Chen
Technical Fellow & CVP
Microsoft
Noam Brown
Noam Brown
Research Scientist
OpenAI
Sida Wang
Sida Wang
Research Scientist
Meta
James Zou
James Zou
Professor
Stanford
Clay Bavor
Clay Bavor
Co-Founder
Sierra
Oriol Vinyals
Oriol Vinyals
VP, Research
Google DeepMind
Peter Stone
Peter Stone
Chief Scientist at Sony Al, Professor at UT Austin
Sony AI

Class Time and Location

Lecture: 3-5pm PT Monday (starts Sep 15, 2025)

Course Description

Agentic AI is the new frontier and poised to transform the future of our daily life with the support of intelligent task automation and personalization. In this course, we will first discuss fundamental concepts that are essential for Agentic AI, including the foundation of LLMs, reasonsing, planning, agentic frameworks and infrastructure. We will also cover representative agent applications, including code generation, robotics, web automation, and scientific discovery. Meanwhile, we will discuss limitations and potential risks of current LLM agents, and share insights into directions for further improvement.

Syllabus

Date Lecture
(3:10PM-5:00PM PT)
Supplemental Readings
Sep 15 LLM Agents Overview
Yann Dubois, OpenAI
[Slides] [Recording] [Quiz]
- KIMI K2: Open Agentic Intelligence
- DeepSeek-V3 Technical Report
Sep 22 Evolution of system designs from an AI engineer perspective
Yangqing Jia, NVIDIA
[Slides] [Recording] [Quiz]
Sep 29 Post-Training Verifiable Agents
Jiantao Jiao, NVIDIA
[Slides] [Recording] [Quiz]
- Introducing SWE-bench Verified
- BrowseComp: a benchmark for browsing agents
Oct 6 Agent Evaluation & Project Overview
[Slides] [Recording] [Quiz]
- Survey on Evaluation of LLM-based Agents
Oct 13 Some Challenges and Lessons from Training Agentic Models
Weizhu Chen, Microsoft
[Slides] [Recording] [Quiz]
Oct 20 Multi-Agent AI
Noam Brown, OpenAI
[Slides] [Recording] [Quiz]
Oct 27 Predictable Noise in LLM
Sida Wang, Meta
[Slides] [Recording] [Quiz]
- Adding Error Bars to Evals: A Statistical Approach to Language Model Evaluations
Nov 3 AI Agents to Automate Scientific Discoveries
James Zou, Stanford
[Recording] [Quiz]
- The Virtual Lab of AI agents designs new SARS-CoV-2 nanobodies
- Paper2Agent: Reimagining Research Papers As Interactive and Reliable AI Agents
Nov 10 Practical Lessons from Deploying Real-World AI Agents
Clay Bavor, Sierra
[Slides] [Live Stream]
- τ2-Bench: Evaluating Conversational Agents in a Dual-Control Environment
- Voice Sims: test agents in real world conditions before they talk to customers
Nov 17 Oriol Vinyals, Google DeepMind
Nov 24 Peter Stone, UT Austin / Sony AI
Dec 1 Agentic AI Safety & Security
Dawn Song, UC Berkeley
Dec 8 No lecture — RRR week

 

Completion Certificate

Course completion certificates will be awarded to students based on the rules of the following tiers. All assignments are due late December (tentatively December 16th, 2025 at 11:59PM PDT). To receive your certificate please complete the Certificate Declaration Form by late December (tentatively December 16th, 2025 at 11:59PM PDT). This form will be released in November.

Trailblazer Tier:

Mastery Tier:

Legendary Tier:

Honorary Tier:

Earn Your Certificate in 3 Steps

STEP 1. Complete all of the coursework for your desired tier.

STEP 2. Complete the Certificate Declaration Form.

STEP 3. Certificates will be sent to your email in Spring 2026!

NOTE: You can only earn one certificate from this course (not counting Honorary Tier). Completing the assignments associated with this course in order to earn a Completion Certificate is completely optional. You are more than welcome to just watch the lectures and audit the course!

Coursework

All coursework will be released and submitted through the course website.

Quizzes

All quizzes are released shortly after the corresponding lecture and are graded on completion. Please remember to complete the quiz each week. Although it’s graded on completion, we encourage you to do your best. The questions are all multiple-choice and there are usually 5 per quiz. The quizzes will be posted in the Syllabus section.

Written Article

Create a social media post (X/LinkedIn/etc) of roughly 500 words. Include the link to our MOOC website in the article and post.

The written article is an effort-based assignment that will be graded as pass or no pass (P/NP). The submission form will be released later – stay tuned!

AgentX-AgentBeats Competition

More information about the project can be found at AgentX-AgentBeats.

Questions?

We are so excited to have you join us this semester! If you have any questions, please reach out to the course staff in our LLM Agents Discord.