A Neurodiversity-Inspired Solver for the Abstraction \& Reasoning Corpus (ARC) Using Visual Imagery and Program Synthesis

TL;DR

This paper introduces a neurodiversity-inspired AI system that combines visual mental imagery and program synthesis to improve reasoning on the challenging ARC tasks, achieving competitive results.

Contribution

It presents a novel approach integrating visual representations inspired by neurodivergent cognition with program synthesis for flexible reasoning in AI.

Findings

Achieved 4th place in the 2022 ARCathon challenge.

Demonstrated effectiveness on publicly available ARC items.

Showed potential of neurodiversity-inspired methods in AI reasoning.

Abstract

Core knowledge about physical objects -- e.g., their permanency, spatial transformations, and interactions -- is one of the most fundamental building blocks of biological intelligence across humans and non-human animals. While AI techniques in certain domains (e.g. vision, NLP) have advanced dramatically in recent years, no current AI systems can yet match human abilities in flexibly applying core knowledge to solve novel tasks. We propose a new AI approach to core knowledge that combines 1) visual representations of core knowledge inspired by human mental imagery abilities, especially as observed in studies of neurodivergent individuals; with 2) tree-search-based program synthesis for flexibly combining core knowledge to form new reasoning strategies on the fly. We demonstrate our system's performance on the very difficult Abstraction \& Reasoning Corpus (ARC) challenge, and we share experimental results from publicly available ARC items as well as from our 4th-place finish on the private test set during the 2022 global ARCathon challenge.