Google’s Dream-RSI cuts AI discovery costs by replaying past searches

AI discovery is the use of AI agents to search through many possible solutions, experiments, or algorithms. The agents generate ideas, test them, evaluate the results, and refine their search to find better outcomes faster. Google DeepMind’s Dream-RSI lets AI agents test thousands of search strategies against recorded attempts instead of rerunning expensive experiments. In tests across eight algorithmic, mathematical, and GPU tasks, the approach reduced discovery-agent calls by up to 162 times and helped Gemini find a faster statistical solver in 317 attempts, compared with 550 for a fixed strategy and 51,200 for SimpleTES.
Source

👉@sysadminoff

https://4sysops.com/archives/googles-dream-rsi-cuts-ai-discovery-costs-by-replaying-past-searches/