NSA: Neuro-symbolic ARC Challenge
On the map: LLM reasoning → Multimodal reasoning
Abstract (arXiv)
The Abstraction and Reasoning Corpus (ARC) evaluates general reasoning capabilities that are difficult for both machine learning models and combinatorial search methods. We propose a neuro-symbolic approach that combines a transformer for proposal generation with combinatorial search using a domain-specific language. The transformer narrows the search space by proposing promising search directions, which allows the combinatorial search to find the actual solution in short time. We pre-train the trainsformer with synthetically generated data. During test-time we generate additional task-specific training tasks and fine-tune our model. Our results surpass comparable state of the art on the ARC evaluation set by 27% and compare favourably on the ARC train set. We make our code and dataset publicly available at https://github.com/Batorskq/NSA.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Multimodal reasoning, one of 17 directions in LLM reasoning. Builds on 21 of its 29 references that are in the map. First posted on arXiv 8 Jan 2025.
Builds on
21 of 29 references.
Closest ancestors · 4
Same direction, newest first
- 2024Tackling the Abstraction and Reasoning Corpus with Vision Transformers: the Importance of 2D Representation, Positions, and Objects8 Oct
- 2024CodeIt: Self-Improving Language Models with Prioritized Hindsight Replay7 Feb
- 2023Comparing Humans, GPT-4, and GPT-4V On Abstraction and Reasoning Tasks14 Nov
- 2023LLMs and the Abstraction and Reasoning Corpus: Successes, Failures, and the Importance of Object-based Representations26 May
Other references · 17
- 2017Attention Is All You Needcited by 59,932
- 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
- 2023GPT-4 Technical Reportcited by 18,132
- 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
- 2024GPT-4o System Cardcited by 4,467
- 2021Decision Transformer: Reinforcement Learning via Sequence Modelingcited by 1,528
- 2023Large Language Models as General Pattern Machinescited by 196
- 2020DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learningcited by 159
- 2023Hypothesis Search: Inductive Reasoning with Language Modelscited by 119
- 2023The ConceptARC Benchmark: Evaluating Understanding and Generalization in the ARC Domaincited by 97
- 2021Fast and flexible: Human program induction in abstract reasoning taskscited by 33
- 2022Graphs, Constraints, and Search for the Abstraction and Reasoning Corpuscited by 32
5 more
- 2021Neural-guided, Bidirectional Program Search for Abstraction and Reasoningcited by 23
- 2021First Steps of an Approach to the ARC Challenge based on Descriptive Grid Models and the Minimum Description Length Principlecited by 13
- 2023Unraveling the ARC Puzzle: Mimicking Human Solutions with Object-Centric Decision Transformercited by 12
- 2024Generalized Planning for the Abstraction and Reasoning Corpuscited by 10
- 2023Tackling the Abstraction and Reasoning Corpus (ARC) with Object-centric Models and the MDL Principlecited by 6
Built on by
Citing papers per year: 2025: 1; 2026: 1.
2 papers.
Similar, not cited
Close in wording, no citation either way
- 2026Compositional Neuro-Symbolic Reasoning
- 2024Neural networks for abstraction and reasoning: Towards broad generalization in machines
- 2025Tiny Recursive Models on ARC-AGI-1: Inductive Biases, Identity Conditioning, and Test-Time Compute
- 2026PotARCin: Multi-Dimensional Evaluation of Skill Acquisition in Abstract Reasoning Tasks
- 2025Don't throw the baby out with the bathwater: How and why deep learning for ARC
- 2025ARC-NCA: Towards Developmental Solutions to the Abstraction and Reasoning Corpus
- 2024The Role of Foundation Models in Neuro-Symbolic Learning and Reasoning
- 2024Abductive Symbolic Solver on Abstraction and Reasoning Corpus