Beating RL With Reflection: GEPA and Optimize Anything — Lakshya A. Agrawal, GEPA

After one round of reflection on just three examples, GEPA doubled the gains that the RL algorithm GRPO reached after 25,000 rollouts. Lakshya A. Agrawal, creator of GEPA and a PhD student at UC Berkeley's Sky Computing Lab, explains why. RL squeezes a whole rollout down to a single score. GEPA instead has a model read the full trace, including chains of thought, tool calls and error messages, and write a better prompt. A Pareto pool of candidates keeps the search out of local optima. The same idea works on anything you can write as text and score, which is where Optimize Anything comes in. Agrawal shows it taking a four-line program to a six-step agent that lifts Gemini Flash on ARC-AGI from 32.5% to 89.5%. It pushed an AMD NPU coding agent from 4% to 30%, and improved a GPT-5 mini coding agent on Go issues from 24% to 93%, using learned skills that also carried over to Claude Sonnet. He also covers Databricks tuning an open model to beat Claude Opus at 90x lower cost, learning evals from production traces, and co-optimizing prompts and weights. Speaker info: X/Twitter: @LakshyAAAgrawal (https://x.com/LakshyAAAgrawal) LinkedIn: https://www.linkedin.com/in/lakshyaaagrawal/ Website: https://lakshyaaagrawal.github.io/ Related links: GEPA on GitHub: https://github.com/gepa-ai/gepa Timestamps: 0:00 Intro: reflective optimization 0:30 How we teach AI new tasks 1:00 The sample-efficiency bottleneck 2:05 What RL throws away 3:00 Reflecting in text space 4:25 GEPA 4:50 GEPA vs. GRPO: 3 examples vs. 25,000 rollouts 5:40 What GEPA learns 6:55 GPT-4.1 mini beats GPT-4.1 7:15 A new AMD NPU: 4% to 30% 8:25 How GEPA works 9:00 Why a Pareto pool beats a simple loop 10:10 Results across benchmarks 10:35 Beyond prompts: Optimize Anything 12:05 The API 12:55 A 3D unicorn 13:35 Discovering agent harnesses: ARC-AGI from 32.5% to 89.5% 14:40 MATH-500 15:10 Optimizing agent skills: 24% to 93% 16:40 Three optimization modes 17:30 In production: OCR and a 90x cheaper agent 18:40 Why better models need better prompts 19:10 Learning evals from production traces 19:55 Fast-slow learning: prompts and weights 20:20 Who uses GEPA 20:45 Get started