ARC-NCA: Towards Developmental Solutions to the Abstraction and Reasoning Corpus

TL;DR

This paper presents ARC-NCA, a developmental neural approach using Neural Cellular Automata to address the ARC-AGI challenge, demonstrating promising results comparable to advanced AI models at lower cost.

Contribution

Introducing a developmental neural approach with NCA and EngramNCA for solving the ARC-AGI benchmark, inspired by biological development processes.

Findings

ARC-NCA achieves competitive performance on ARC-AGI tasks.

Developmental principles enhance AI reasoning and abstraction.

Potential for cost-effective, adaptive AI solutions.

Abstract

The Abstraction and Reasoning Corpus (ARC), later renamed ARC-AGI, poses a fundamental challenge in artificial general intelligence (AGI), requiring solutions that exhibit robust abstraction and reasoning capabilities across diverse tasks, while only few (with median count of three) correct examples are presented. While ARC-AGI remains very challenging for artificial intelligence systems, it is rather easy for humans. This paper introduces ARC-NCA, a developmental approach leveraging standard Neural Cellular Automata (NCA) and NCA enhanced with hidden memories (EngramNCA) to tackle the ARC-AGI benchmark. NCAs are employed for their inherent ability to simulate complex dynamics and emergent patterns, mimicking developmental processes observed in biological systems. Developmental solutions may offer a promising avenue for enhancing AI's problem-solving capabilities beyond mere training data extrapolation. ARC-NCA demonstrates how integrating developmental principles into computational models can foster adaptive reasoning and abstraction. We show that our ARC-NCA proof-of-concept results may be comparable to, and sometimes surpass, that of ChatGPT 4.5, at a fraction of the cost.