用发育式神经元自动机解决抽象推理难题，效果媲美大模型但成本更低。
ARC-NCA: Towards Developmental Solutions to the Abstraction and Reasoning Corpus
- 基于神经元自动机模拟发育过程，自动生成解题模式。
- 仅用三个示例即达接近GPT-4.5的推理水平。
- 适合研究通用人工智能与低成本高效模型设计者。
抽象与推理语料库（ARC），后更名为ARC-AGI，对通用人工智能（AGI）构成根本挑战，要求系统在仅有少数（中位数为三个）正确示例的情况下，展现出跨任务的鲁棒抽象与推理能力。尽管对人工智能仍极具挑战性，人类却能轻松应对。本文提出ARC-NCA，一种基于标准神经元自动机（NCA）及引入隐藏记忆的增强型NCA（EngramNCA）的发育式方法，用于应对ARC-AGI基准测试。NCAs因其能够模拟复杂动态与涌现模式，类比生物系统的发育过程，具备潜力突破单纯训练数据外推的局限。实验表明，该方法在概念验证层面表现可媲美甚至超越ChatGPT 4.5，且成本仅为后者的极小部分。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。