百度发布自动研究系统 ERNIE Evolve，可根据明确研究目标选择研究方向、修改代码并运行实验，只有通过独立评估与审核的改进才会保留，每轮结果指导下一轮。该系统在 NanoChat AutoResearch 和 NanoGPT Speedrun 上取得 SOTA，GPU 确定性推理吞吐提升 33.7%，单请求解码速度提升 14.9%。
同一件事，精选收录的是《百度文心披露 RSI 系统 ERNIE Evolve，已用于文心 5.5 Flash 推理优化》
Introducing ERNIE Evolve, our automated research system for improving AI training and inference. ⚙️
Given a clear research goal, it selects research directions, modifies code and runs experiments. Only improvements that pass independent evaluation and review are kept, and each round’s findings guide the next.
From public benchmarks to ERNIE 5.5 Flash inference tests, here’s what it achieved:
- SOTA on NanoChat AutoResearch and NanoGPT Speedrun
- 33.7% higher deterministic GPU inference throughput
- 14.9% faster single-request decoding on GPUs
This is a practical step toward recursive self-improvement (RSI). Next, we plan to extend this approach to training systems, model capabilities and evaluation.
来源：Baidu Inc. · x.com