Neural-guided, Bidirectional Program Search for Abstraction and Reasoning

TL;DR

This paper introduces a neural-guided, bidirectional program search method for systematic reasoning and abstraction, advancing AI's ability to generalize to new visual reasoning tasks like ARC.

Contribution

It presents a novel neural-guided, bidirectional search algorithm and applies program synthesis for abstraction, improving performance on complex reasoning tasks.

Findings

Effective on ARC, 24-Game, and arithmetic puzzles

Enables solving more challenging ARC tasks

Demonstrates the potential of neural-guided, bidirectional reasoning

Abstract

One of the challenges facing artificial intelligence research today is designing systems capable of utilizing systematic reasoning to generalize to new tasks. The Abstraction and Reasoning Corpus (ARC) measures such a capability through a set of visual reasoning tasks. In this paper we report incremental progress on ARC and lay the foundations for two approaches to abstraction and reasoning not based in brute-force search. We first apply an existing program synthesis system called DreamCoder to create symbolic abstractions out of tasks solved so far, and show how it enables solving of progressively more challenging ARC tasks. Second, we design a reasoning algorithm motivated by the way humans approach ARC. Our algorithm constructs a search graph and reasons over this graph structure to discover task solutions. More specifically, we extend existing execution-guided program synthesis approaches with deductive reasoning based on function inverse semantics to enable a neural-guided bidirectional search algorithm. We demonstrate the effectiveness of the algorithm on three domains: ARC, 24-Game tasks, and a 'double-and-add' arithmetic puzzle.