Teaching LLMs to Self-Reflect with Reinforcement Learning with Maohao Shen - #726

The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)

Content provided by TWIML and Sam Charrington. All podcast content including episodes, graphics, and podcast descriptions are uploaded and provided directly by TWIML and Sam Charrington or their podcast platform partner. If you believe someone is using your copyrighted work without your permission, you can follow the process outlined here https://player.fm/legal.

19d ago 51:45

MP3•Episode home

Today, we're joined by Maohao Shen, PhD student at MIT to discuss his paper, “Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search.” We dig into how Satori leverages reinforcement learning to improve language model reasoning—enabling model self-reflection, self-correction, and exploration of alternative solutions. We explore the Chain-of-Action-Thought (COAT) approach, which uses special tokens—continue, reflect, and explore—to guide the model through distinct reasoning actions, allowing it to navigate complex reasoning tasks without external supervision. We also break down Satori’s two-stage training process: format tuning, which teaches the model to understand and utilize the special action tokens, and reinforcement learning, which optimizes reasoning through trial-and-error self-improvement. We cover key techniques such “restart and explore,” which allows the model to self-correct and generalize beyond its training domain. Finally, Maohao reviews Satori’s performance and how it compares to other models, the reward design, the benchmarks used, and the surprising observations made during the research.

The complete show notes for this episode can be found at https://twimlai.com/go/726.

747 episodes

#Artificial Intelligence #Tech News #Artificialintelligence #Machinelearning #Samcharrington #Technology #Thisweekinmachinelearning #Sam Charrington #Thetwimlaipocast #Twimlaipodcast #Tech #News #China #TWIML #Datascience #Science