Skip to content

Source paper

GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning

Lakshya A Agrawal, Shangyin Tan, Dilara Soylu and 14 more

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

arXiv 2507.19457 · 202530 upvotes on Hugging Face

Research ideas from this paper (3)

Generated by AI. The paper’s authors did not write these.

AI summary

This paper introduces GEPA (Genetic-Pareto), a prompt optimization algorithm for compound AI systems that outperforms Reinforcement Learning (RL) methods like GRPO. GEPA uses natural language reflection to mutate prompts based on execution traces and maintains a Pareto frontier of diverse candidates to avoid local optima, achieving higher performance with significantly fewer rollouts.

How it works (AI summary)

GEPA employs an evolutionary algorithm where 'Reflective Prompt Mutation' uses an LLM to analyze failure traces and propose improvements, while 'Pareto-based Candidate Selection' preserves population diversity by keeping prompts that excel on specific task subsets rather than just a single global best.