Skip to content
Stanford CS329A Self-Improving AI Agents | Part 4 | Learning from Feedback with Tools/Code episode artwork

Nov 14, 2026 1 hr 17 min

Stanford CS329A Self-Improving AI Agents | Part 4 | Learning from Feedback with Tools/Code

from Stanford Online: University Courses & Lectures Hosted by Stanford Online

Want to dive deeper? This curriculum is covered in the following online courses:- Agentic AI professional education course: https://learn.stanford.edu/agentic-ai-2026.html- XCS329 graduate course: https://online.stanford.edu/courses/cs329a-self-improving-ai-agentsUploaded 03-08-26A similar curriculum is covered in XCS329z https://online.stanford.edu/courses/cs329z-engineering-ai-agentsFollow along with the course schedule and syllabus: https://cs329a.stanford.edu/Aakanksha ChowdheryAdjunct Professor of Computer Science, Stanford UniversityView the course playlist: https://www.youtube.com/playlist?list=PLangBM27OtEAVideo Summary:This lecture recording from Stanford's CS329A, Self-Improving AI Agents, taught by Aakanksha Chowdhery on October 3, 2025, covers three approaches to improving language models through feedback. ReAct interleaves chain-of-thought reasoning with tool-calling actions and is evaluated on HotpotQA, FEVER, and WebShop. RLEF, or Reinforcement Learning from Execution Feedback, trains coding agents using public and private unit test results within a PPO training loop, evaluated on CodeContests. Constitutional AI, developed by Anthropic, uses a written set of principles along with model self-critique and revision to train a preference model through reinforcement learning from AI feedback rather than human feedback. The lecture compares how each method sources its feedback signal, from environment interaction to execution results to AI-generated critique, and reviews related work including WebGPT, Code Monkeys, and SWE-bench.Speaker Bio:Aakanksha ChowdheryAdjunct Professor of Computer Science, Stanford UniversityDr. Aakanksha Chowdhery is pushing the frontier of agentic LLMs, focusing on recursive self-improvement and long-horizon agents that learn and deploy in the real world. She is one of the few researchers globally who has led frontier model training end-to-end, across both dense and mixture-of-experts (MoE) architectures. At Google, she led the 540B PaLM model, the largest densely trained language model in the world at the time. She subsequently drove pre-training and scaling of Gemini's MoE models across multiple generations, and contributed key components to PaLM-E, Med-PaLM, and the Pathways infrastructure underpinning Google's large-model efforts. She went on to build and lead pretraining teams for open intelligence efforts at Reflection and Meta. Earlier, she held research roles at Microsoft Research and Princeton. At Stanford, where she earned her PhD, she teaches CS329A (Self-Improving AI Agents) and serves as Program Chair for MLSys 2026.

Episode details come from the podcast's RSS feed.

Embed this episode

Ready to play

Stanford CS329A Self-Improving AI Agents | Part 4 | Learning from Feedback with Tools/Code

0:00 1:17:57

No transcript yet.

Requests help us decide what to transcribe next.

The Course Mentors Podcast The Course Mentors Hey there, future course creator! Ever feel like turning your know-how into an online course is like trying to solve a Rubik's cube blindfolded? Well, grab your headphones because "The Course Mentors Podcast" is here to be your secret weapon! Meet Aimee and Odette (that's us!), your new best friends in the course creation world. We've been in the trenches for over a decade, and for the last five years, we've been rocking the online course space. Now we're here to spill all our secrets in bite-sized, 15-20 minute episodes that'll fit perfectly in your coffee breaks. No fluff, no filler - just real, actionable advice that'll take you from "um, what's a landing page?" to "holy moly, I just hit six figures!". We're talking everything from crafting your course to marketing it like a pro and building a business that'll have you pinching yourself. Whether you're dreaming of ditching the 9-to-5 grind, adding a sweet extra income str The Bitcoin Standard Podcast Dr. Saifedean Ammous Saifedean's The Bitcoin Standard Podcast is the place to discuss Bitcoin and economics from the Austrian school's perspective. Listen to the weekly saifedean.com discussion seminar, where a group of learners from all over the world discuss the website's online courses, as well as a wide variety of economic, political, and social issues, and occasionally host special guests for the discussion. The podcast also includes the most interesting interviews conducted with Saifedean on other shows.

Frequently asked questions

How long is this episode of Stanford Online: University Courses & Lectures?

This episode is 1 hour and 17 minutes long.

When was this Stanford Online: University Courses & Lectures episode published?

This episode was published on November 14, 2026.

Can I download this Stanford Online: University Courses & Lectures episode?

Yes. Use the download control on the episode player to save the publisher-provided media file.