GEPA

GEPA is a prompt optimization method in which a language model reflects on execution traces to rewrite prompts and evolves candidates through Pareto-based selection.

1 articleLast mentioned

GEPA (Genetic-Pareto) is a prompt optimization method published in 2025 by researchers from UC Berkeley, Stanford University, Databricks and other institutions. A language model reflects in natural language on the execution traces and evaluation results of a multi-step AI system, diagnoses the causes of failure, and rewrites the prompt of each step accordingly. Candidates that achieve the best score on at least one evaluation example are kept on a Pareto frontier, so that candidates with different strengths continue to be developed.

Because it does not modify model weights, GEPA can be applied to models that are accessible only through an API. It is available as an open-source library and as an optimizer in the prompt programming framework DSPy.

This entry is based on AIPOST articles and widely known facts. If something is wrong, please send us a correction request.

Articles covering this entry

  • AI Agent Tuning: When to Rewrite Prompts and When to Retrain WeightsAI Performance ·

    GEPA, short for Genetic Pareto Prompt Evolution, keeps a pool of prompt candidates scored across many tasks.

    Read article

Found a mistake or missing an entry?

Wiki entries are based on AIPOST articles and widely known facts. If an entry is wrong, send us a correction request and we will check and fix it. Names from new articles are added to the wiki after the article is published.