# GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning

arXiv: https://arxiv.org/abs/2507.19457 · HTML: https://mlsanity.com/paper/2507.19457/

## Key facts

- Cited by 542 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning for reasoning, one of 17 directions in LLM reasoning.
- First posted on arXiv 25 Jul 2025.

## Placed in

- LLM reasoning / [Reinforcement learning for reasoning](https://mlsanity.com/lr/reinforcement-learning-for-reasoning/)

## Built on by (most cited first, 30 of 542)

- [Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models](https://mlsanity.com/paper/2510.04618/) (2025)
- [Meta-Harness: End-to-End Optimization of Model Harnesses](https://mlsanity.com/paper/2603.28052/) (2026)
- [SkillOpt: Executive Strategy for Self-Evolving Agent Skills](https://mlsanity.com/paper/2605.23904/) (2026)
- [Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses](https://mlsanity.com/paper/2604.25850/) (2026)
- [The Attacker Moves Second: Stronger Adaptive Attacks Bypass Defenses Against Llm Jailbreaks and Prompt Injections](https://mlsanity.com/paper/2510.09023/) (2025)
- [EvoSkill: Automated Skill Discovery for Multi-Agent Systems](https://mlsanity.com/paper/2603.02766/) (2026)
- [WoW: Towards a World omniscient World model Through Embodied Interaction](https://mlsanity.com/paper/2509.22642/) (2025)
- [ThetaEvolve: Test-time Learning on Open Problems](https://mlsanity.com/paper/2511.23473/) (2025)
- [Memento-Skills: Let Agents Design Agents](https://mlsanity.com/paper/2603.18743/) (2026)
- [AdaEvolve: Adaptive LLM Driven Zeroth-Order Optimization](https://mlsanity.com/paper/2602.20133/) (2026)
- [EvoX: Meta-Evolution for Automated Discovery](https://mlsanity.com/paper/2602.23413/) (2026)
- [Barbarians at the Gate: How AI is Upending Systems Research](https://mlsanity.com/paper/2510.06189/) (2025)
- [Expanding the Capabilities of Reinforcement Learning via Text Feedback](https://mlsanity.com/paper/2602.02482/) (2026)
- [FLEX: Continuous Agent Evolution via Forward Learning from Experience](https://mlsanity.com/paper/2511.06449/) (2025)
- [CORAL: Towards Autonomous Multi-Agent Evolution for Open-Ended Discovery](https://mlsanity.com/paper/2604.01658/) (2026)
- [Astra: A Multi-Agent System for GPU Kernel Performance Optimization](https://mlsanity.com/paper/2509.07506/) (2025)
- [Meta Context Engineering via Agentic Skill Evolution](https://mlsanity.com/paper/2601.21557/) (2026)
- [Rethinking the Evaluation of Harness Evolution for Agents](https://mlsanity.com/paper/2607.12227/) (2026)
- [Skill-Pro: Learning Reusable Skills from Experience via Non-Parametric PPO for LLM Agents](https://mlsanity.com/paper/2602.01869/) (2026)
- [Code as Agent Harness](https://mlsanity.com/paper/2605.18747/) (2026)
- [Feedback Descent: Open-Ended Text Optimization via Pairwise Comparison](https://mlsanity.com/paper/2511.07919/) (2025)
- [Continual Harness: Online Adaptation for Self-Improving Foundation Agents](https://mlsanity.com/paper/2605.09998/) (2026)
- [Recursive Self-Aggregation Unlocks Deep Thinking in Large Language Models](https://mlsanity.com/paper/2509.26626/) (2025)
- [Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents](https://mlsanity.com/paper/2605.30621/) (2026)
- [Recursive Harness Self-Improvement](https://mlsanity.com/paper/2607.15524/) (2026)
- [From Failed Trajectories to Reliable LLM Agents: Diagnosing and Repairing Harness Flaws](https://mlsanity.com/paper/2606.06324/) (2026)
- [Where Did It All Go Wrong? A Hierarchical Look into Multi-Agent Error Attribution](https://mlsanity.com/paper/2510.04886/) (2025)
- [Hidden in Memory: Sleeper Memory Poisoning in LLM Agents](https://mlsanity.com/paper/2605.15338/) (2026)
- [Reasoning Models Struggle to Control their Chains of Thought](https://mlsanity.com/paper/2603.05706/) (2026)
- [From Static Templates to Dynamic Runtime Graphs: A Survey of Workflow Optimization for LLM Agents](https://mlsanity.com/paper/2603.22386/) (2026)

## Abstract (arXiv)

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 rollouts to learn new tasks. We argue that the interpretable nature of language often provides a much richer learning medium for LLMs, compared to policy gradients derived from sparse, scalar rewards. To test this, we introduce GEPA (Genetic-Pareto), a prompt optimizer that thoroughly incorporates natural language reflection to learn high-level rules from trial and error. Given any AI system containing one or more LLM prompts, GEPA samples trajectories (e.g., reasoning, tool calls, and tool outputs) and reflects on them in natural language to diagnose problems, propose and test prompt updates, and combine complementary lessons from the Pareto frontier of its own attempts. As a result of GEPA's design, it can often turn even just a few rollouts into a large quality gain. Across six tasks, GEPA outperforms GRPO by 6% on average and by up to 20%, while using up to 35x fewer rollouts. GEPA also outperforms the leading prompt optimizer, MIPROv2, by over 10% (e.g., +12% accuracy on AIME-2025), and demonstrates promising results as an inference-time search strategy for code optimization. We release our code at https://github.com/gepa-ai/gepa .