Dream-RSI paper: improving search strategy alone cuts AI discovery compute up to 162x

r0ck3t23 · x · 2026-09-19

Researchers from Google, Google DeepMind, the University of Maryland and the University of Virginia present Dream-RSI, a way to make AI systems stronger without touching model weights.

Reported gains:

The takeaway: capability progress isn't only about better weights — improving how efficiently a system searches the capability it already has can unlock a lot of it.

Related event: Google DeepMind's Dream-RSI: Recursive Self-Improvement Through Replaying Past Discoveries(15 posts)→

Original post →

More from Research

Research channel →