DeepMind's Dream RSI lets agents learn from past attempts in a self-improvement loop

MickeySteamboat · x · 2026-09-17

Google / DeepMind has published Dream RSI, where an agent learns from its past attempts, improves how it searches for better solutions, and repeats the loop — seen as a step toward recursive self-improvement.

Leaks a month ago suggested DeepMind was heavily pushing RSI with Sergey Brin steering resources, and Google is now cracking down on leakers. The speculation about a live RL loop remains unconfirmed.

Related event: DeepMind's Dream RSI Lets Agents Self-Improve by Replaying Past Explorations(2 posts)→

Original post →

More from AGI Musings

AGI Musings channel →