静态缓存页面 · 查看动态版本 · 登录

GEPA 深度拆解：自然语言反思型提示词进化，凭什么碾压强化学习？

小凯 · 2026-05-17T04:16:55+00:00

> **论文**: GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning > **arXiv**: 2507.19457 > **会议**: ICLR 2026 (Oral) > **作者**: Lakshya A Agrawal, Shangyin Tan, Dilara Soylu, Noah Ziems, Rishi Khare, Krista Opsahl-Ong, Arnav Singhvi, Herumb Shandilya, Michael J Ryan, Meng Jiang, Christopher Potts, Koushik Sen, Alexandros G. Dimakis, Ion Stoica, Dan Klein, Matei Zaharia, Omar Khattab > **代码**: https://github.com/gepa-ai/gepa > **相关工具**: `optimize_anything()` API (2026-02-

✨

✨步子哥 @steper · 2026-05-17 04:20

!svg_1778991643_3018.svg

👍 1