Lakshya A Agrawal

Stop what you are doing and try out GEPA now!

"GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning" presents such elegant ideas by a collection of amazing researchers!

Here is a tldr of how it works:

GEPA (Genetic-Pareto) is a sample-efficient prompt optimization method for compound AI systems that works by reflectively evolving prompts using natural language feedback instead of traditional scalar rewards.

In each iteration, GEPA samples system rollouts (including reasoning traces, tool outputs, and any diagnostic text), reflects on them via an LLM to identify issues or propose improvements, and updates specific module prompts accordingly based on the feedback.

To ensure diversity and avoid local optima, GEPA maintains a pool of candidates and uses Pareto-based selection, which keeps all non-dominated strategies discovered so far and stochastically proposes new prompt variants, enabling robust generalization with far fewer rollouts than reinforcement

1. GEPA Overview - DSPy The framework for programming—rather than prompting—language models.

GEPA: prompt optimization can exceed RL performance

They used Qwen3-8B (which was not trained for math, coding, agency, etc.) and show that GEPA performed better than RL rollouts

paper: arxiv.org/abs/2507.19457

github: github.com/gepa-ai/gepa

DSPy docs: dspy.ai/api/optimize...

Automating Agentic Prompts: A new algorithm called GEPA, developed by researchers at UC Berkeley, Stanford, and other institutions, improves the performance of agentic systems by automatically refining their prompts.

AGI is just around the corner!

I'm learning to use DSPy with GEPA (Genetic-Pareto) prompt optimization. In GEPA a larger "teacher" LLM adjusts the prompt for a smaller "student" LM to perform a specific task as well as possible. The teacher will try many different prompts and evaluate the […]

Hey, would love to get any feedback on how you'd think about improving the interface

Agent多步誤差咋破？看下GEPA，反思自進化 帕累託前沿，超過DSPy的MIPROv2 來自UC Berkeley，斯坦福的Genetic-Pareto Prompt Optimizer

Agent多步誤差咋破？看下GEPA，反思自進化 帕累託前沿，超過DSPy的MIPROv2 #反思 #誤差 #超過

Just what I was looking for. Thank you for sharing, looking forward to the read.

GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning 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...

propose and test prompt updates, and combine complementary lessons from the Pareto frontier of its own attempts.

arxiv.org/abs/2507.19457

DSPy folks love GEPA, so here's a GEPA paper for anyone who wants to learn more.

Given any AI system containing one or more LLM prompts, GEPA samples system-level trajectories (e.g., reasoning, tool calls, and tool outputs) and reflects on them in natural language to diagnose problems,

ArXiv page 7

..GEPA and prompt optimization explained: https://arxiv.org/abs/2507.19457v1

(7/7)

ArXiv page 6

..make adapting large models more practical—especially when compute or data is limited. It’s like giving AI a way to learn from its own “thinking out loud,” turning natural language into a powerful tool for self-improvement.

Links:
Paper on arXiv: https://arxiv.org/abs/2507.19457 ..

(6/7)

ArXiv page 5

..code on the fly.

What’s cool here is the shift from treating AI tuning as a blind search for a higher score to a reflective process that leverages the AI’s native strength: language. By evolving prompts through thoughtful reflections, GEPA unlocks smarter, faster learning that could..

(5/7)

ArXiv page 4

..fewer attempts than traditional reinforcement learning methods. On several tough tasks like multi-step question answering and instruction following, GEPA consistently outperforms both standard reinforcement learning and previous prompt optimizers. It even shows promise for optimizing..

(4/7)

ArXiv page 3

..strategies by mixing and matching what works best.

GEPA treats AI prompt tuning like a conversation with itself, iterating through generations of prompts that learn from detailed feedback written in words, not just numbers. This lets it learn much more efficiently—up to 35 times..

(3/7)

ArXiv page 2

..what went wrong and how to fix it? That’s the idea behind a new approach called GEPA. Instead of relying solely on those sparse reward signals, GEPA has AI inspect its own attempts using natural language reflections. It diagnoses errors, proposes prompt fixes, and evolves smarter..

(2/7)

ArXiv page 1

What if language itself could teach AI to get better, faster?

Most AI training feels like trial and error in the dark—reinforcement learning tweaks models by chasing a number, often needing tens of thousands of tries to improve. But what if the AI could actually *talk to itself* about..

(1/7)

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

gepa 0.0.15a1 A framework for optimizing textual system components (AI prompts, code snippets, etc.) using LLM-based reflection and Pareto-efficient evolutionary search.


Origin | Interest | Match

gepa 0.0.15a1 A framework for optimizing textual system components (AI prompts, code snippets, etc.) using LLM-based reflection and Pareto-efficient evolutionary search.

Interest | Match | Feed

gepa 0.0.15a1 A framework for optimizing textual system components (AI prompts, code snippets, etc.) using LLM-based reflection and Pareto-efficient evolutionary search.

Interest | Match | Feed

gepa 0.0.16 A framework for optimizing textual system components (AI prompts, code snippets, etc.) using LLM-based reflection and Pareto-efficient evolutionary search.

Interest | Match | Feed

gepa 0.0.16 A framework for optimizing textual system components (AI prompts, code snippets, etc.) using LLM-based reflection and Pareto-efficient evolutionary search.

Interest | Match | Feed

New research released today from Databricks shows how its GEPA (Generative Evolutionary Prompt Adaptation) technique improves prompt optimization by an order of magnitude.

venturebeat.com/ai/the-usd10...

🚀 #GEPA: Automatic #Prompt Optimization by @databricksinc.bsky.social: gpt-oss-120b beats Claude Sonnet 4 (+3%) at ~20x lower cost. Completes with DSPy SIMBA/MIPROv2
📜 MIT lic
🔗 Link in first 💬⤵️

Repost 🔁 #AI #LLM #RAG #PromptEngineering #ContextEngineering

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

⭐️🔗 GitHub: github.com/gepa-ai/gepa
⭐️🔗 www.databricks.com/blog/buildin...
👉 Discuss with me in Discord: linktr.ee/qdrddr

Lessons & Practices for Building and Optimizing Multi-Agent RAG Systems with DSPy and GEPA Introduction When I first read “Building and Optimizing Multi-Agent RAG Systems with DSPy and GEPA”...

Lessons & Practices for Building and Optimizing Multi-Agent RAG Systems with DSPy and GEPA https://cstu.io/cbe4bb #love #techno #future

Screenshot of the repository

optimizes prompts and code using AI-driven reflection and evolution

https://github.com/gepa-ai/gepa