Get the latest tech news

GEPA: Reflective prompt evolution can outperform reinforcement learning


Authors: 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.

Authors: 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 Paper: https://arxiv.org/abs/2507.19457 This feedback isn't just a number; it's a rich, textual record of the entire process, including the LLM's own reasoning chains, the specific tool calls it made, and even detailed diagnostic information from the evaluation environment, like compiler error messages or failed unit tests. An example of a GEPA-generated prompt (Figure 2) reveals a level of detail and strategic insight far beyond a simple instruction, including sections on "Key Observations," "Purpose and Context," and "Practical Strategy."

Get the Android app

Or read this on Hacker News

Read more on:

Photo of gepa

gepa