Code Evolution Tree

Baidu released ERNIE Evolve, an automated research system that edits AI training and inference code and keeps only verified gains via two nested loops: a Director steering research directions with parallel code-evolution trees, plus a hidden Evaluator and Reviewer to reject eval-gaming candidates. It scored 0.8763 BPB on NanoChat AutoResearch, 38.9 s on NanoGPT Speedrun Track 1, and pushed Kunlunxin P800 inference to 623.6% of baseline. The system itself is not open-sourced; only final benchmark code and run logs were released.