self-improving AI

Google and DeepMind researchers introduced Dream-RSI, a method that lets AI agents test new search strategies by replaying recorded past attempts instead of running costly new computations. Tested on Gemini 3.1 Pro and Gemini 3.7 Flash across eight tasks, it matched or beat baselines while using far fewer attempts.

A new Anthropic paper from its fellows program shows an automated AI system improving performance on all 10 tested alignment benchmarks, outperforming experienced human researchers within six hours at a fraction of the cost. The research, led by Anthropic Fellow Chen Yueh-Han, is described as early evidence that automated alignment post-training could become practical soon.