Sakana AI Wins GECCO Best Paper Award

SakanaAILabs · x · 2026-07-20

Sakana AI's paper, "In Search of the Elements of Openness: Reproducing Picbreeder with Large Vision-Language Models," won the Best Paper Award in the Complex Systems track at GECCO 2026. The research attempts to use AI agents to recreate the classic Picbreeder evolutionary experiment, utilizing Vision-Language Models (VLMs) to evolve CPPN images, which users can then branch, rate, and inspect.

Related event: Sakana AI Wins Best Paper Award at GECCO 2026(2 posts)→

Original post →

More from Research

Research channel →