CausalARC: Abstract Reasoning with Causal World Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Maasch, Jacqueline, Kalantari, John, Khezeli, Kia
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908901095505920
author Maasch, Jacqueline
Kalantari, John
Khezeli, Kia
author_facet Maasch, Jacqueline
Kalantari, John
Khezeli, Kia
contents On-the-fly reasoning often requires adaptation to novel problems under limited data and distribution shift. This work introduces CausalARC: an experimental testbed for AI reasoning in low-data and out-of-distribution regimes, modeled after the Abstraction and Reasoning Corpus (ARC). Each CausalARC reasoning task is sampled from a fully specified causal world model, formally expressed as a structural causal model. Principled data augmentations provide observational, interventional, and counterfactual feedback about the world model in the form of few-shot, in-context learning demonstrations. As a proof-of-concept, we illustrate the use of CausalARC for four language model evaluation settings: (1) abstract reasoning with test-time training, (2) counterfactual reasoning with in-context learning, (3) program synthesis, and (4) causal discovery with logical reasoning. Within- and between-model performance varied heavily across tasks, indicating room for significant improvement in language model reasoning.
format Preprint
id arxiv_https___arxiv_org_abs_2509_03636
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CausalARC: Abstract Reasoning with Causal World Models
Maasch, Jacqueline
Kalantari, John
Khezeli, Kia
Artificial Intelligence
Computation and Language
Machine Learning
On-the-fly reasoning often requires adaptation to novel problems under limited data and distribution shift. This work introduces CausalARC: an experimental testbed for AI reasoning in low-data and out-of-distribution regimes, modeled after the Abstraction and Reasoning Corpus (ARC). Each CausalARC reasoning task is sampled from a fully specified causal world model, formally expressed as a structural causal model. Principled data augmentations provide observational, interventional, and counterfactual feedback about the world model in the form of few-shot, in-context learning demonstrations. As a proof-of-concept, we illustrate the use of CausalARC for four language model evaluation settings: (1) abstract reasoning with test-time training, (2) counterfactual reasoning with in-context learning, (3) program synthesis, and (4) causal discovery with logical reasoning. Within- and between-model performance varied heavily across tasks, indicating room for significant improvement in language model reasoning.
title CausalARC: Abstract Reasoning with Causal World Models
topic Artificial Intelligence
Computation and Language
Machine Learning
url https://arxiv.org/abs/2509.03636