NEW Regularized RSI & Medical RSI (Google, Stanford)

New Idea: the intelligence of AI machines scales via the scaffolding (harness, runtime control), not the core LLM parameters. And it needs something from DARWIN for the best evolutionary environment: Selection. all rights w/ authors: RRSI: Regularized Recursive Self-Improvement of Agent Harnesses Peng Xia1,2*, Rujun Han1, Zifeng Wang1, Yanfei Chen1, Yufan Zhang1, Yoonho Lee3, Chengsong Huang4, Han Yu1, Zhongying CuiZhu1, Yifei Ming1, Huaxiu Yao2, Burak Gokturk1, Tomas Pfister1 and Chen-Yu Lee1