Large language models (LLMs) are increasingly adapted to downstream tasks via reinforcement learning (RL) methods like Group Relative Policy Optimization (GRPO), which often require thousands of rollo...

GEPA's new API setting state-of-the-art results on optimizing any text parameter: code, prompts, agent architectures, and more. If you can measure it, you can optimize it.

GEPA's new API setting state-of-the-art results on optimizing any text parameter: code, prompts, agent architectures, and more. If you can measure it, you can optimize it.

The framework for programming—rather than prompting—language models.

來自UC Berkeley，斯坦福的Genetic-Pareto Prompt Optimizer

Large language models (LLMs) are increasingly adapted to downstream tasks via reinforcement learning (RL) methods like Group Relative Policy Optimization (GRPO), which often require thousands of rollo...

A framework for optimizing textual system components (AI prompts, code snippets, etc.) using LLM-based reflection and Pareto-efficient evolutionary search.

Optimize prompts, code, and more with AI-powered Reflective Text Evolution - gepa-ai/gepa

While the entire industry chases the next AI hype, tools that truly transform engineering practices often get lost in the noise. DSPy and its optimizer GEPA are prime examples — they’re quietly…

prompt engineering experiments with DSPy GEPA and TextGrad - Laurian/context-compression-experiments-2508

Moving beyond the slow, costly trial-and-error of RL, GEPA teaches AI systems to learn and improve using natural language.

Want smarter insights in your inbox? Sign up for our weekly newsletters to get only what matters to enterprise AI, data, and security leaders. Subscribe Now Researchers from the University of California, Berkeley, Stanford University and Databricks have introduced a new AI optimization method called GEPA that significantly outperforms traditional reinforcement learning (RL) techniques for adapting large language models (LLMs) to specialized tasks. GEPA removes the popular paradigm of learning through thousands of trial-and-error attempts guided by simple numerical scores. Instead, it uses an LLM’s own language understanding to reflect on its performance, diagnose errors, and iteratively evolve its instructions.

Want smarter insights in your inbox? Sign up for our weekly newsletters to get only what matters to enterprise AI, data, and security leaders. Subscribe Now Researchers from the University of California, Berkeley, Stanford University and Databricks have introduced a new AI optimization method called GEPA that significantly outperforms traditional reinforcement learning (RL) techniques for adapting large language models (LLMs) to specialized tasks. GEPA removes the popular paradigm of learning through thousands of trial-and-error attempts guided by simple numerical scores. Instead, it uses an LLM’s own language understanding to reflect on its performance, diagnose errors, and iteratively evolve its instructions.

Moving beyond the slow, costly trial-and-error of RL, GEPA teaches AI systems to learn and improve using natural language.