mlsanityData to 7 Oct 2026

The ARC of Progress towards AGI: A Living Survey of Abstraction and Reasoning

arXiv 2603.13372 ↗First posted 9 Mar 2026cs.AI cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

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/

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 26 of its 54 references that are in the map. First posted on arXiv 9 Mar 2026.

Builds on

26 of 54 references.

References · 26

  1. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  2. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  3. 2020Measuring Massive Multitask Language Understandingcited by 7,768
  4. 2021Program Synthesis with Large Language Modelscited by 3,509
  5. 2022Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language modelscited by 1,970
  6. 2020COGS: A Compositional Generalization Challenge Based on Semantic Interpretationcited by 260
  7. 2018BabyAI: A Platform to Study the Sample Efficiency of Grounded Language Learningcited by 238
  8. 2019RAVEN: A Dataset for Relational and Analogical Visual rEasoNingcited by 225
  9. 2020The NetHack Learning Environmentcited by 196
  10. 2021Benchmarking the Spectrum of Agent Capabilitiescited by 193
  11. 2025Wider or Deeper? Scaling LLM Inference-Time Compute with Adaptive Branching Tree Searchcited by 48
  12. 2025Self-Improving Language Models for Evolutionary Program Synthesis: A Case Study on ARC-AGIcited by 34
14 more
  1. 2024H-ARC: A Robust Estimate of Human Performance on the Abstraction and Reasoning Corpus Benchmarkcited by 32
  2. 2025ArcMemo: Abstract Reasoning Composition with Lifelong LLM Memorycited by 22
  3. 2025Assessing Adaptive World Models in Machines with Novel Gamescited by 20
  4. 2025Product of Experts with LLMs: Boosting Performance on ARC Is a Matter of Perspectivecited by 17
  5. 2024Towards Efficient Neurally-Guided Program Induction for ARC-AGIcited by 11
  6. 2025Neural Cellular Automata for ARC-AGIcited by 9
  7. 2024ConceptSearch: Towards Efficient Program Search Using LLMs for Abstraction and Reasoning Corpus (ARC)cited by 8
  8. 2025From Generation to Generalization: Emergent Few-Shot Learning in Video Diffusion Modelscited by 7
  9. 2025Don't throw the baby out with the bathwater: How and why deep learning for ARCcited by 7
  10. 2023Infusing Lattice Symmetry Priors in Attention Mechanisms for Sample-Efficient Abstract Geometric Reasoningcited by 4
  11. 2025MADIL: An MDL-based Framework for Efficient Program Synthesis in the ARC Benchmarkcited by 3
  12. 2023Computational Models of Solving Raven's Progressive Matrices: A Comprehensive Introductioncited by 2
  13. 2024Abductive Symbolic Solver on Abstraction and Reasoning Corpuscited by 2
  14. 2025Out-of-Distribution Generalization in the ARC-AGI Domain: Comparing Execution-Guided Neural Program Synthesis and Test-Time Fine-Tuningcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026Tycho: Active Abstraction with Programmatic World Models for ARC-AGI-3cited by 5
  2. 2026Loop the Loopies!cited by 4
  3. 2026Language-Guided Abstraction for Visual Reasoningcited by 0
  4. 2026DiARC: Distinguishing Positive and Negative Samples Helps Improving ARC-like Reasoning Ability of Large Language Modelscited by 0