mlsanityData to 14 Oct 2026

Vector Symbolic Algebras for the Abstraction and Reasoning Corpus

arXiv 2511.08747 ↗First posted 11 Nov 2025cs.AI cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

The Abstraction and Reasoning Corpus for Artificial General Intelligence (ARC-AGI) is a generative, few-shot fluid intelligence benchmark. Although humans effortlessly solve ARC-AGI, it remains extremely difficult for even the most advanced artificial intelligence systems. Inspired by methods for modelling human intelligence spanning neuroscience to psychology, we propose a cognitively plausible ARC-AGI solver. Our solver integrates System 1 intuitions with System 2 reasoning in an efficient and interpretable process using neurosymbolic methods based on Vector Symbolic Algebras (VSAs). Our solver works by object-centric program synthesis, leveraging VSAs to represent abstract objects, guide solution search, and enable sample-efficient neural learning. Preliminary results indicate success, with our solver scoring 10.8% on ARC-AGI-1-Train and 3.0% on ARC-AGI-1-Eval. Additionally, our solver performs well on simpler benchmarks, scoring 94.5% on Sort-of-ARC and 83.1% on 1D-ARC -- the latter outperforming GPT-4 at a tiny fraction of the computational cost. Importantly, our approach is unique; we believe we are the first to apply VSAs to ARC-AGI and have developed the most cognitively plausible ARC-AGI solver yet. Our code is available at: https://github.com/ijoffe/ARC-VSA-2025.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 45 of its 118 references that are in the map. First posted on arXiv 11 Nov 2025.

Builds on

45 of 118 references.

References · 45

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2023GPT-4 Technical Reportcited by 18,396
  4. 2013Intriguing properties of neural networkscited by 5,155
  5. 2022Emergent Abilities of Large Language Modelscited by 2,512
  6. 2014Deep Learning in Neural Networks: An Overviewcited by 770
  7. 2023The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"cited by 407
  8. 2020Neurosymbolic AI: The 3rd Wavecited by 255
  9. 2023Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Taskscited by 246
  10. 2025ARC-AGI-2: A New Challenge for Frontier AI Reasoning Systemscited by 190
  11. 2025Hierarchical Reasoning Modelcited by 177
  12. 2023How well do Large Language Models perform in Arithmetic tasks?cited by 130
33 more
  1. 2023Hypothesis Search: Inductive Reasoning with Language Modelscited by 120
  2. 2023LLMs and the Abstraction and Reasoning Corpus: Successes, Failures, and the Importance of Object-based Representationscited by 82
  3. 2023Comparing Humans, GPT-4, and GPT-4V On Abstraction and Reasoning Taskscited by 55
  4. 2024Combining Induction and Transduction for Abstract Reasoningcited by 53
  5. 2021Computing on Functions Using Randomized Vector Representationscited by 41
  6. 2024Why Do Large Language Models (LLMs) Struggle to Count Letters?cited by 38
  7. 2021Vector Symbolic Architectures as a Computing Framework for Emerging Hardwarecited by 35
  8. 2021Communicating Natural Programs to Humans and Machinescited by 35
  9. 2021Fast and flexible: Human program induction in abstract reasoning taskscited by 33
  10. 2024Addressing the Abstraction and Reasoning Corpus via Procedural Example Generationcited by 33
  11. 2024H-ARC: A Robust Estimate of Human Performance on the Abstraction and Reasoning Corpus Benchmarkcited by 33
  12. 2022Graphs, Constraints, and Search for the Abstraction and Reasoning Corpuscited by 32
  13. 2024Reasoning Abilities of Large Language Models: In-Depth Analysis on the Abstraction and Reasoning Corpuscited by 32
  14. 2024When Can Transformers Count to n?cited by 24
  15. 2025Product of Experts with LLMs: Boosting Performance on ARC Is a Matter of Perspectivecited by 17
  16. 2023Assessing GPT4-V on Structured Reasoning Taskscited by 14
  17. 2024Neural networks for abstraction and reasoning: Towards broad generalization in machinescited by 13
  18. 2023Counting and Algorithmic Generalization with Transformerscited by 12
  19. 2024Towards Efficient Neurally-Guided Program Induction for ARC-AGIcited by 11
  20. 2024Neuro-Symbolic AI: Explainability, Challenges, and Future Trendscited by 10
  21. 2023Solving ARC visual analogies with neural embeddings and vector arithmetic: A generalized methodcited by 8
  22. 2023Tackling the Abstraction and Reasoning Corpus (ARC) with Object-centric Models and the MDL Principlecited by 7
  23. 2024Do Large Language Models Solve ARC Visual Analogies Like People Do?cited by 7
  24. 2025Don't throw the baby out with the bathwater: How and why deep learning for ARCcited by 7
  25. 2024Relational decomposition for program synthesiscited by 6
  26. 2020A short letter on the dot product between rotated Fourier transformscited by 5
  27. 2024Program Synthesis using Inductive Logic Programming for the Abstraction and Reasoning Corpuscited by 4
  28. 2021Systematic human learning and generalization from a brief tutorial with explanatory feedbackcited by 2
  29. 2024Show, Don't Tell: Evaluating Large Language Models Beyond Textual Understanding with ChildPlaycited by 2
  30. 2024Abductive Symbolic Solver on Abstraction and Reasoning Corpuscited by 2
  31. 2025Hey Pentti, We Did It!: A Fully Vector-Symbolic Lispcited by 2
  32. 2024Intelligence Analysis of Language Modelscited by 1
  33. 2024Learning to Solve Abstract Reasoning Problems with Neurosymbolic Program Synthesis and Task Generationcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026ARC Prize 2025: Technical Reportcited by 4