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

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Guichard, Etienne, Reimers, Felix, Kvalsund, Mia, Lepperød, Mikkel, Nichele, Stefano
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866915286526984192
author Guichard, Etienne
Reimers, Felix
Kvalsund, Mia
Lepperød, Mikkel
Nichele, Stefano
author_facet Guichard, Etienne
Reimers, Felix
Kvalsund, Mia
Lepperød, Mikkel
Nichele, Stefano
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_08778
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ARC-NCA: Towards Developmental Solutions to the Abstraction and Reasoning Corpus
Guichard, Etienne
Reimers, Felix
Kvalsund, Mia
Lepperød, Mikkel
Nichele, Stefano
Artificial Intelligence
Neural and Evolutionary Computing
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.
title ARC-NCA: Towards Developmental Solutions to the Abstraction and Reasoning Corpus
topic Artificial Intelligence
Neural and Evolutionary Computing
url https://arxiv.org/abs/2505.08778