NSA: Neuro-symbolic ARC Challenge

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Batorski, Paweł, Brinkmann, Jannik, Swoboda, Paul
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917548463751168
author Batorski, Paweł
Brinkmann, Jannik
Swoboda, Paul
author_facet Batorski, Paweł
Brinkmann, Jannik
Swoboda, Paul
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2501_04424
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle NSA: Neuro-symbolic ARC Challenge
Batorski, Paweł
Brinkmann, Jannik
Swoboda, Paul
Artificial Intelligence
Computation and Language
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.
title NSA: Neuro-symbolic ARC Challenge
topic Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2501.04424