The ARC of Progress towards AGI: A Living Survey of Abstraction and Reasoning
TIB - Leibniz Information Centre for Science and Technology(TIB - 科学技术信息研究中心);L3S Research Center, Leibniz University of Hannover(L3S研究所以汉诺威莱布尼茨大学);Dresden University of Technology, Amazon (work done outside of Amazon)(德累斯顿技术大学,亚马逊(非亚马逊工作))
Sahar Vahdati, Andrei Aioanei, Haridhra Suresh, Jens Lehmann
The Abstraction and Reasoning Corpus (ARC-AGI) has become a key benchmark for fluid intelligence in AI. This survey presents the first cross-generation analysis of 82 approaches across three benchmark versions and the ARC Prize 2024-2025 competitions. Our central finding is that performance degradation across versions is consistent across all paradigms: program synthesis, neuro-symbolic, and neural approaches all exhibit 2-3x drops from ARC-AGI-1 to ARC-AGI-2, indicating fundamental limitations in compositional generalization. While systems now reach 93.0% on ARC-AGI-1 (Opus 4.6), performance falls to 68.8% on ARC-AGI-2 and 13% on ARC-AGI-3, as humans maintain near-perfect accuracy across all versions. Cost fell 390x in one year (o3's $4,500/task to GPT-5.2's $12/task), although this largely reflects reduced test-time parallelism. Trillion-scale models vary widely in score and cost, while Kaggle-constrained entries (660M-8B) achieve competitive results, aligning with Chollet's thesis that intelligence is skill-acquisition efficiency. Test-time adaptation and refinement loops emerge as critical success factors, while compositional reasoning and interactive learning remain unsolved. ARC Prize 2025 winners needed hundreds of thousands of synthetic examples to reach 24% on ARC-AGI-2, confirming that reasoning remains knowledge-bound. This first release of the ARC-AGI Living Survey captures the field as of February 2026, with updates at https://nimi-ai.com/arc-survey/
Vector Symbolic Algebras for the Abstraction and Reasoning Corpus
Centre for Theoretical Neuroscience(理论神经科学中心);David R. Cheriton School of Computer Science(大卫·R·切里顿计算机科学学院);University of Waterloo(滑铁库大学);Department of Philosophy(哲学系);Department of Systems Design Engineering(系统设计工程系)
Tycho: Active Abstraction with Programmatic World Models for ARC-AGI-3
Dresden University of Technology(德累斯顿工业大学);Amazon(亚马逊);TIB – Leibniz Information Centre for Science and Technology(莱布尼茨科学与技术信息中心);Leibniz University of Hannover(汉诺威莱布尼茨大学)
Can Complexity and Uncomputability Explain Intelligence? SuperARC: A Test for Artificial Super Intelligence Based on Recursive Compression
Oxford Immune Algorithmics(牛津免疫算法公司);Oxford University Innovation(牛津大学创新中心);London Institute for Healthcare Engineering(伦敦医疗工程研究所);Algorithmic Dynamics Lab(算法动力实验室);Center of Molecular Medicine, Karolinska Institute(卡罗林斯卡研究所分子医学中心);King’s College London(伦敦大学国王学院);Centre for Logic, Epistemology and the History of Science, University of Campinas (UNICAMP)(逻辑、知识论和科学史研究中心,坎皮纳斯大学);DEXL, National Laboratory for Scientific Computing (LNCC)(DEXL,国家科学计算实验室);King’s Institute for Artificial Intelligence, King’s College London(伦敦大学国王学院人工智能研究所)