2 papers
cs.LG2025
Self-Improving Language Models for Evolutionary Program Synthesis: A Case Study on ARC-AGI
Julien Pourcel, Cédric Colas, Pierre-Yves Oudeyer
Many program synthesis tasks prove too challenging for even state-of-the-art language models to solve in single attempts. Search-based evolutionary methods offer a promising altern…
cs.LG2023
ACES: Generating Diverse Programming Puzzles with with Autotelic Generative Models
Julien Pourcel, Cédric Colas, Gaia Molinaro +2
The ability to invent novel and interesting problems is a remarkable feature of human intelligence that drives innovation, art, and science. We propose a method that aims to automa…