The Abstract Reasoning Corpus (ARC) is an intelligence tests for measuring fluid intelligence in artificial intelligence systems and humans alike. In this paper we present a system for reasoning about and solving ARC tasks. Our system relies on a program synthesis approach that searches a space of potential programs for ones that can solve tasks from the ARC. Programs are in a domain specific language, and in some instances our search algorithm is guided by insights from a corpus of ground truth programs. In particular: We describe an imperative style domain specific language, called Visual Imagery Reasoning Language (VIMRL), for reasoning about tasks in the ARC. We also demonstrate an innovative approach for how large search spaces can be decomposed using special high level functions that determine their own arguments through local searches on a given task item. Finally, we share our results obtained on the publicly available ARC items as well as our system's strong performance on a private test, recently tying for 4th place on the global ARCathon 2022 challenge.
翻译:《解释公司摘要》(ARC)是测量人工智能系统和人类的流体智能的一种情报测试。在本文中,我们提出了一个解释和解决 ARC 任务的系统。我们的系统依赖于一种程序合成方法,为那些能够从 ARC 中解决问题的人搜索潜在程序的空间。程序使用一种特定的领域语言,在某些情况下,我们的搜索算法以一组地面真相方案的洞察力为指导。特别是:我们描述了一种需要的风格特定域语言,即所谓的视觉图像解释语言(VIMRL),用于解释 ARC 中的任务。我们还展示了一种创新方法,即如何利用特别的高级功能使大型搜索空间分解成形,这些功能通过对特定任务项目进行本地搜索来决定它们自己的论点。最后,我们分享了在公开提供的 ARC 项上获得的结果,以及我们系统在一项私人测试上的有力表现,最近将全球 ARCathon 2022 挑战的第四个位置连接在一起。</s>