Abductive Symbolic Solver on Abstraction and Reasoning Corpus

TL;DR

This paper introduces an abductive symbolic reasoning framework for the Abstraction and Reasoning Corpus, aiming to improve AI's logical reasoning and solution explainability by leveraging knowledge graphs to narrow the search space.

Contribution

It proposes a novel symbolic approach that models observed data as knowledge graphs and extracts core knowledge to generate human-like, logical solutions for visual reasoning tasks.

Findings

Enhanced reasoning accuracy on ARC tasks

Reduced solution search space through core knowledge extraction

Improved explainability of AI solutions

Abstract

This paper addresses the challenge of enhancing artificial intelligence reasoning capabilities, focusing on logicality within the Abstraction and Reasoning Corpus (ARC). Humans solve such visual reasoning tasks based on their observations and hypotheses, and they can explain their solutions with a proper reason. However, many previous approaches focused only on the grid transition and it is not enough for AI to provide reasonable and human-like solutions. By considering the human process of solving visual reasoning tasks, we have concluded that the thinking process is likely the abductive reasoning process. Thus, we propose a novel framework that symbolically represents the observed data into a knowledge graph and extracts core knowledge that can be used for solution generation. This information limits the solution search space and helps provide a reasonable mid-process. Our approach holds promise for improving AI performance on ARC tasks by effectively narrowing the solution space and providing logical solutions grounded in core knowledge extraction.