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

arXiv: https://arxiv.org/abs/2505.08778 · HTML: https://mlsanity.com/paper/2505.08778/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 15 of its 33 references that are in the map.
- First posted on arXiv 13 May 2025.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)

## Builds on (most cited first, 15 of 15)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [ARC Prize 2024: Technical Report](https://mlsanity.com/paper/2412.04604/) (2024)
- [LLMs and the Abstraction and Reasoning Corpus: Successes, Failures, and the Importance of Object-based Representations](https://mlsanity.com/paper/2305.18354/) (2023)
- [Predictive Coding: a Theoretical and Experimental Review](https://mlsanity.com/paper/2107.12979/) (2021)
- [Cellular automata as convolutional neural networks](https://mlsanity.com/paper/1809.02942/) (2018)
- [Growing 3D Artefacts and Functional Machines with Neural Cellular Automata](https://mlsanity.com/paper/2103.08737/) (2021)
- [Attention-based Neural Cellular Automata](https://mlsanity.com/paper/2211.01233/) (2022)
- [Towards self-organized control: Using neural cellular automata to robustly control a cart-pole agent](https://mlsanity.com/paper/2106.15240/) (2021)
- [Biomaker CA: a Biome Maker project using Cellular Automata](https://mlsanity.com/paper/2307.09320/) (2023)
- [CAX: Cellular Automata Accelerated in JAX](https://mlsanity.com/paper/2410.02651/) (2024)
- [EngramNCA: a Neural Cellular Automaton Model of Memory Transfer](https://mlsanity.com/paper/2504.11855/) (2025)
- [Learning Elementary Cellular Automata with Transformers](https://mlsanity.com/paper/2412.01417/) (2024)
- [A Unified Substrate for Body-Brain Co-evolution](https://mlsanity.com/paper/2203.12066/) (2022)
- [Neural Cellular Automata Can Respond to Signals](https://mlsanity.com/paper/2305.12971/) (2023)
- [Latent Neural Cellular Automata for Resource-Efficient Image Restoration](https://mlsanity.com/paper/2403.15525/) (2024)

## Built on by (most cited first, 10 of 10)

- [Neural Cellular Automata for ARC-AGI](https://mlsanity.com/paper/2506.15746/) (2025)
- [Neural cellular automata: applications to biology and beyond classical AI](https://mlsanity.com/paper/2509.11131/) (2025)
- [Neural Cellular Automata: From Cells to Pixels](https://mlsanity.com/paper/2506.22899/) (2025)
- [ARC Prize 2025: Technical Report](https://mlsanity.com/paper/2601.10904/) (2026)
- [Learning Developmental Scaffoldings to Guide Self-Organisation](https://mlsanity.com/paper/2605.14998/) (2026)
- [BraiNCA: brain-inspired neural cellular automata and applications to morphogenesis and motor control](https://mlsanity.com/paper/2604.01932/) (2026)
- [Neural Cellular Automata Learn General Features in their Hidden Channels](https://mlsanity.com/paper/2609.21870/) (2026)
- [Architecture Generalization with MetaNCA](https://mlsanity.com/paper/2607.07743/) (2026)
- [On Growth and Form, and Function: Reusable Regulatory Handles Control Phenotypic Variation](https://mlsanity.com/paper/2609.29755/) (2026)
- [Reasoning with Neural Cellular Automata](https://mlsanity.com/paper/2609.36126/) (2026)

## Abstract (arXiv)

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.