GEPA-Curator filters agent experiences before prompt optimization
On four agent benchmarks it gains up to 20.7% over GEPA and 21.2% over ACE with Gemini 3.1 Pro and Claude Opus 5.
Stories per day · 30 days
Relatedprompt-optimization2ablation1agent-harness1agentmark1agents1benchmarks1claude-code1language-models1provenance1self-evolution1self-improving-agents1watermarking1
3 stories, newest first · one card per story
Stories tagged #gepa
Study traces GEPA merge instability to configuration, not the operator
A nine-configuration sweep across five datasets finds merge can help both gpt-4.1-mini and Qwen3-8B.
What Survives Self-Evolution: Provenance Marks in Copied Agent Harnesses
Provenance marks in leaked agent harnesses mostly fail when a self-evolving LLM rewrites the marked code.