# Google's Dream-RSI Improves Agent Search Strategy Without Touching Model Weights

Replaying past discovery trees as offline simulators cut agent calls by up to 162 times against a search baseline on one task, the authors report.

- Published: 2026-09-29T06:12:03.689Z
- Canonical: https://polylog.news/ai/2026-09-29/google-s-dream-rsi-improves-agent-search-strategy-without-to
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [Polylog editors](https://polylog.news)

Google, Google DeepMind and university collaborators published Dream-RSI, a layer that sits above agents that solve problems by generating candidate code, scoring it with an evaluator, and refining the best results. The system leaves the ge…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-09-29/google-s-dream-rsi-improves-agent-search-strategy-without-to (subscription information: https://polylog.news/pricing).