Automated Search for Artificial Life

The Automated Search for Artificial Life (ASAL) algorithm was proposed by Sakana AI in December 2024 in collaboration with MIT, OpenAI, Swiss AI Laboratory IDSIA and other institutions. The relevant research results were published in the paper "Automating the Search for Artificial Life with Foundation Models".

ASAL aims to automatically explore the simulation space in the field of Artificial Life (ALife) using Foundation Models. This technology enables AI to autonomously discover new artificial life forms without the need for tedious manual design processes. The algorithm has proven its effectiveness in a variety of classic ALife matrices, including Boids, Particle Life, Game of Life, Lenia, and Neural Cellular Automata. Through ASAL, researchers have discovered unprecedented life forms, such as strange clustering patterns in Boids, new self-organizing cells in Lenia, and open cellular automata similar to Conway's Game of Life.