XNews

Google and DeepMind's Dream-RSI Cuts Agent Calls 162x via Recursive Self-Improvement

Google and DeepMind's Dream-RSI Cuts Agent Calls 162x via Recursive Self-Improvement

Google and DeepMind demonstrated Dream-RSI, an AI recursive self-improvement loop that replays past discoveries to test exploration strategies, reducing agent calls by up to 162x while maintaining or improving results in algorithm design, math optimization, and GPU kernel engineering.

Source posts