Baidu Unveils ERNIE Evolve to Auto-Evolve Training and Inference Code
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.
Related Entities
Full Report
▲ Marktechpost AI · 2026-11-09 16
▲ Baidu just released ERNIE Evolve, an automated research system that edits AI training and inference code and keeps only verified gains.
The key idea is 2 nested loops. A Director picks research directions, and parallel lanes evolve trees of code versions. A hidden Evaluator outside the repo scores each candidate, and a Reviewer discards anything that games the eval.
On public benchmarks it hit 0.8763 BPB on NanoChat AutoResearch (best public: 0.8878) and 38.9 s on NanoGPT Speedrun Track 1 (record: 39.9 s). On ERNIE-5.5-Flash it pushed Kunlunxin P800 speed to 623.6% of baseline and deterministic GPU throughput up 33.7%. It is a trade-off though: SOL-ExecBench came in at 0.819, behind the 0.827 leader, and a 6.7 s Speedrun claim posted Oct 28 already moves that bar.
The system itself is not released. Baidu open-sourced the final code and run logs for the public benchmark results......
Full analysis:
