# CellARC: Measuring Intelligence with Cellular Automata

arXiv: https://arxiv.org/abs/2511.07908 · HTML: https://mlsanity.com/paper/2511.07908/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 43 references that are in the map.
- First posted on arXiv 11 Nov 2025.

## Builds on (most cited first, 15 of 15)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [GLU Variants Improve Transformer](https://mlsanity.com/paper/2002.05202/) (2020)
- [Root Mean Square Layer Normalization](https://mlsanity.com/paper/1910.07467/) (2019)
- [On First-Order Meta-Learning Algorithms](https://mlsanity.com/paper/1803.02999/) (2018)
- [Universal Transformers](https://mlsanity.com/paper/1807.03819/) (2018)
- [Neural Turing Machines](https://mlsanity.com/paper/1410.5401/) (2014)
- [Adaptive Computation Time for Recurrent Neural Networks](https://mlsanity.com/paper/1603.08983/) (2016)
- [ARC-AGI-2: A New Challenge for Frontier AI Reasoning Systems](https://mlsanity.com/paper/2505.11831/) (2025)
- [Neural GPUs Learn Algorithms](https://mlsanity.com/paper/1511.08228/) (2015)
- [Addressing the Abstraction and Reasoning Corpus via Procedural Example Generation](https://mlsanity.com/paper/2404.07353/) (2024)
- [CAX: Cellular Automata Accelerated in JAX](https://mlsanity.com/paper/2410.02651/) (2024)

## Built on by (most cited first, 1 of 1)

- [Tape: A Cellular Automata Benchmark for Evaluating Rule-Shift Generalization in Reinforcement Learning](https://mlsanity.com/paper/2601.04695/) (2026)

## Abstract (arXiv)

We introduce CellARC, a synthetic benchmark for abstraction and reasoning built from multicolor 1D cellular automata (CA). Each episode has five support pairs and one query serialized in 256 tokens, enabling rapid iteration with small models while exposing a controllable task space with explicit knobs for alphabet size k, radius r, rule family, Langton's lambda, query coverage, and cell entropy. We release 95k training episodes plus two 1k test splits (interpolation/extrapolation) and evaluate symbolic, recurrent, convolutional, transformer, recursive, and LLM baselines. CellARC decouples generalization from anthropomorphic priors, supports unlimited difficulty-controlled sampling, and enables reproducible studies of how quickly models infer new rules under tight budgets. Our strongest small-model baseline (a 10M-parameter vanilla transformer) outperforms recent recursive models (TRM, HRM), reaching 58.0%/32.4% per-token accuracy on the interpolation/extrapolation splits, while a large closed model (GPT-5 High) attains 62.3%/48.1% on subsets of 100 test tasks. An ensemble that chooses per episode between the Transformer and the best symbolic baseline reaches 65.4%/35.5%, highlighting neuro-symbolic complementarity. Leaderboard: https://cellarc.mireklzicar.com