In Search of the Ingredients of Open-Endedness: Replicating Picbreeder with Large Vision-Language Models
Open Access
- 10 July 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 106-114
Abstract
We are in the midst of large-scale industrial and academic efforts to automate the processes of scientific, technological and creative production through AI-driven assistants. Historically, a fundamental property of these processes in their human form has been their open-endedness: their capacity for generating a seemingly endless supply of novel and meaningful new forms. Do artificial agents have any capacity for such fruitful unguided discovery? To answer this question, we turn to Picbreeder, the canonical exemplar of human-driven open-ended search, in which users collaboratively generated a diverse library of images through interactive evolution of small neural networks. We replicate Picbreeder, replacing human users with frontier Vision Language Models (VLMs). We observe clear qualitative differences between the output of our system and the historical human baseline, and attempt to characterize them using metrics of phylogenetic complexity and visual and semantic salience and novelty. In an effort to identify some of the causal factors contributing these differences, we study the addition of exploratory noise to the agents' selection process, of behavioral diversity between agents, and of narrative momentum in the form of memory of past actions. We make our code available at https://github.com/smearle/picbreeder-vlm.Keywords
This publication has 9 references indexed in Scilit:
- Aligning machine and human visual representations across abstraction levelsNature, 2025
- On the Open-Endedness of Detecting Open-EndednessArtificial Life, 2024
- THINGS-data, a multimodal collection of large-scale datasets for investigating object representations in human brain and behavioreLife, 2023
- Robust, Universal Tree Balance IndicesSystematic Biology, 2022
- Understanding Innovation Engines: Automated Creativity and Improved Stochastic Optimization via Deep LearningEvolutionary Computation, 2016
- Why Greatness Cannot Be Planned2015
- Picbreeder: A Case Study in Collaborative Evolutionary Exploration of Design SpaceEvolutionary Computation, 2011
- What is intrinsic motivation? A typology of computational approachesFrontiers in Neurorobotics, 2007
- Evolving Neural Networks through Augmenting TopologiesEvolutionary Computation, 2002