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

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

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.

Jaksot(781)

From Prompts to Policies: How RL Builds Better AI Agents with Mahesh Sathiamoorthy - #731

From Prompts to Policies: How RL Builds Better AI Agents with Mahesh Sathiamoorthy - #731

Today, we're joined by Mahesh Sathiamoorthy, co-founder and CEO of Bespoke Labs, to discuss how reinforcement learning (RL) is reshaping the way we build custom agents on top of foundation models. Mah...

13 Touko 20251h 1min

How OpenAI Builds AI Agents That Think and Act with Josh Tobin - #730

How OpenAI Builds AI Agents That Think and Act with Josh Tobin - #730

Today, we're joined by Josh Tobin, member of technical staff at OpenAI, to discuss the company’s approach to building AI agents. We cover OpenAI's three agentic offerings—Deep Research for comprehensi...

6 Touko 20251h 7min

CTIBench: Evaluating LLMs in Cyber Threat Intelligence with Nidhi Rastogi - #729

CTIBench: Evaluating LLMs in Cyber Threat Intelligence with Nidhi Rastogi - #729

Today, we're joined by Nidhi Rastogi, assistant professor at Rochester Institute of Technology to discuss Cyber Threat Intelligence (CTI), focusing on her recent project CTIBench—a benchmark for evalu...

30 Huhti 202556min

Generative Benchmarking with Kelly Hong - #728

Generative Benchmarking with Kelly Hong - #728

In this episode, Kelly Hong, a researcher at Chroma, joins us to discuss "Generative Benchmarking," a novel approach to evaluating retrieval systems, like RAG applications, using synthetic data. Kelly...

23 Huhti 202554min

Exploring the Biology of LLMs with Circuit Tracing with Emmanuel Ameisen - #727

Exploring the Biology of LLMs with Circuit Tracing with Emmanuel Ameisen - #727

In this episode, Emmanuel Ameisen, a research engineer at Anthropic, returns to discuss two recent papers: "Circuit Tracing: Revealing Language Model Computational Graphs" and "On the Biology of a Lar...

14 Huhti 20251h 34min

Waymo's Foundation Model for Autonomous Driving with Drago Anguelov - #725

Waymo's Foundation Model for Autonomous Driving with Drago Anguelov - #725

Today, we're joined by Drago Anguelov, head of AI foundations at Waymo, for a deep dive into the role of foundation models in autonomous driving. Drago shares how Waymo is leveraging large-scale machi...

31 Maalis 20251h 9min

Dynamic Token Merging for Efficient Byte-level Language Models with Julie Kallini - #724

Dynamic Token Merging for Efficient Byte-level Language Models with Julie Kallini - #724

Today, we're joined by Julie Kallini, PhD student at Stanford University to discuss her recent papers, “MrT5: Dynamic Token Merging for Efficient Byte-level Language Models” and “Mission: Impossible L...

24 Maalis 202550min

Suosittua kategoriassa Politiikka ja uutiset

uutiscast
aikalisa
ootsa-kuullut-tasta-2
rss-ootsa-kuullut-tasta
tervo-halme
politiikan-puskaradio
rss-vaalirankkurit-podcast
viisupodi
rss-podme-livebox
et-sa-noin-voi-sanoo-esittaa
rss-asiastudio
otetaan-yhdet
the-ulkopolitist
linda-maria
rikosmyytit
radio-antro
rss-sanna-ukkola-show-verkkouutiset
io-techin-tekniikkapodcast
rss-raha-talous-ja-politiikka
rss-tasta-on-kyse-ivan-puopolo-verkkouutiset