XNews

Google and DeepMind demo Dream-RSI loop cutting agent calls by 162x

Google and DeepMind demo Dream-RSI loop cutting agent calls by 162x

Google and DeepMind demonstrated Dream-RSI, a recursive self-improvement loop that replays past discovery processes to cheaply test exploration strategies. Across algorithm design, math optimization, and GPU kernel engineering, it maintained or improved quality while cutting agent calls by up to 162x.

Source posts