{"ID":2875142,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.03636","arxiv_id":"2509.03636","title":"CausalARC: Abstract Reasoning with Causal World Models","abstract":"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.","short_abstract":"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 sam...","url_abs":"https://arxiv.org/abs/2509.03636","url_pdf":"https://arxiv.org/pdf/2509.03636v3","authors":"[\"Jacqueline Maasch\",\"John Kalantari\",\"Kia Khezeli\"]","published":"2025-09-03T18:37:36Z","proceeding":"cs.AI","tasks":"[\"cs.AI\",\"cs.CL\",\"cs.LG\"]","methods":"[\"Language Model\"]","has_code":false}