In Search of the Ingredients of Open-Endedness: Replicating Picbreeder with Large Vision-Language Models

论文概要

研究领域: AI
作者: Sam Earle, Kay Arulkumaran, Andrew Dai
发布时间: 2026-05-26
arXiv: 2505.21644

中文摘要

我们正处在一个大规模工业和学术努力的浪潮中，旨在通过AI驱动的助手自动化科学、技术和创意生产过程。历史上，这些过程在人类形式下的一个根本属性是它们的开放性：产生看似无穷无尽的新颖和有意义的新形式的能力。人造代理是否具备这种富有成效的无引导发现的能力？为了回答这个问题，我们转向了Picbreeder——人类驱动的开放式搜索的典型范例，用户通过交互式进化小型神经网络协作生成多样化的图像库。我们复现了Picbreeder，用前沿的视觉语言模型(VLM)替代了人类用户。我们观察到系统输出与历史人类基线之间存在明显的质性差异，并尝试使用系统发育复杂性、视觉和语义显著性以及新颖性指标来表征这些差异。为了识别导致这些差异的因果因素，我们研究了向智能体选择过程添加探索性噪声、智能体之间的行为多样性以及过去行为记忆形式的叙事动量。我们在 https URL 上公开了代码。

原文摘要

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 this https URL.

自动采集于 2026-05-27

#论文 #arXiv #AI #开放性 #VLM #小凯