Stanford's CS329A Self-Improving AI Agents course: 9 free lectures, 10+ hours on YouTube

techNmak · x · 2026-11-17

Stanford's graduate-level CS329A "Self-Improving AI Agents" course (9 lectures, 10+ hours) is now free on YouTube via Stanford Online, taught by instructors who worked on PaLM, Gemini, and Claude. Topics include test-time compute scaling, robust verification and reward models, learning from tool/code feedback, planning and multi-step reasoning, scaling RL, self-improving and deep research agents, and long-horizon agent evaluation, drawing on work like ReAct, STaR, DeepSeekMath, and AlphaCode.

Original post →

More from coding & agent

coding & agent channel →