# ARC Is a Vision Problem!

arXiv: https://arxiv.org/abs/2511.14761 · HTML: https://mlsanity.com/paper/2511.14761/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Nov 2025.

## Built on by (most cited first, 24 of 24)

- [Fixed-Point Reasoners: Stable and Adaptive Deep Looped Transformers](https://mlsanity.com/paper/2606.18206/) (2026)
- [LoopViT: Scaling Visual ARC with Looped Transformers](https://mlsanity.com/paper/2602.02156/) (2026)
- [Universal Reasoning Model](https://mlsanity.com/paper/2512.14693/) (2025)
- [Reading, Not Thinking: Understanding and Bridging the Modality Gap When Text Becomes Pixels in Multimodal LLMs](https://mlsanity.com/paper/2603.09095/) (2026)
- [Your Reasoning Benchmark May Not Test Reasoning: Revealing Perception Bottleneck in Abstract Reasoning Benchmarks](https://mlsanity.com/paper/2512.21329/) (2025)
- [Kuramoto Oscillatory Phase Encoding: Neuro-inspired Synchronization for Improved Learning Efficiency](https://mlsanity.com/paper/2604.07904/) (2026)
- [One Step Forward and K Steps Back: Better Reasoning with Denoising Recursion Models](https://mlsanity.com/paper/2604.18839/) (2026)
- [Slots, Transitions, Loops: Learning Composable World Models for ARC](https://mlsanity.com/paper/2606.12316/) (2026)
- [Implicit Rule Induction with Test-Time Task Embeddings in ARC-like Tasks](https://mlsanity.com/paper/2609.21181/) (2026)
- [H'an D=an Xu'e B`u (Mimicry) or Q=ing Ch=u Y'u L'an (Mastery)? A Cognitive Perspective on Reasoning Distillation in Large Language Models](https://mlsanity.com/paper/2601.05019/) (2026)
- [Scaling the Scaling Logic: Agentic Meta-Synthesis of Logic Reasoning](https://mlsanity.com/paper/2602.13218/) (2026)
- [PotARCin: Multi-Dimensional Evaluation of Skill Acquisition in Abstract Reasoning Tasks](https://mlsanity.com/paper/2609.27288/) (2026)
- [VISTA: A Visual Harness for Reasoning in an Interactive World](https://mlsanity.com/paper/2610.02200/) (2026)
- [Reasoning is a Modality](https://mlsanity.com/paper/2601.13562/) (2026)
- [Thinking with Drafting: Optical Decompression via Logical Reconstruction](https://mlsanity.com/paper/2602.11731/) (2026)
- [Effort as Ceiling, Not Dial: Reasoning Budget Does Not Modulate Cognitive Cost Alignment Between Humans and Large Reasoning Models](https://mlsanity.com/paper/2605.16938/) (2026)
- [Language-Guided Abstraction for Visual Reasoning](https://mlsanity.com/paper/2606.12847/) (2026)
- [DiARC: Distinguishing Positive and Negative Samples Helps Improving ARC-like Reasoning Ability of Large Language Models](https://mlsanity.com/paper/2606.26530/) (2026)
- [From Global to Factor-Wise Expert Composition in Discrete Diffusion Models](https://mlsanity.com/paper/2607.11758/) (2026)
- [Few-Shot Demonstrations Elicit the Use of In-Context World Representations in LLMs](https://mlsanity.com/paper/2609.24352/) (2026)
- [Intuition vectors](https://mlsanity.com/paper/2609.32619/) (2026)
- [Structured Sparse Memory for Recurrent Reasoning](https://mlsanity.com/paper/2609.33270/) (2026)
- [Reasoning with Neural Cellular Automata](https://mlsanity.com/paper/2609.36126/) (2026)
- [Pretraining and Test-Time Training Budgets Matter for ARC: A Controlled Study of VARC and TRM](https://mlsanity.com/paper/2610.13660/) (2026)

## Abstract (arXiv)

The Abstraction and Reasoning Corpus (ARC) is designed to promote research on abstract reasoning, a fundamental aspect of human intelligence. Common approaches to ARC treat it as a language-oriented problem, addressed by large language models (LLMs) or recurrent reasoning models. However, although the puzzle-like tasks in ARC are inherently visual, existing research has rarely approached the problem from a vision-centric perspective. In this work, we formulate ARC within a vision paradigm, framing it as an image-to-image translation problem. To incorporate visual priors, we represent the inputs on a "canvas" that can be processed like natural images. It is then natural for us to apply standard vision architectures, such as a vanilla Vision Transformer (ViT), to perform image-to-image mapping. Our model is trained from scratch solely on ARC data and generalizes to unseen tasks through test-time training. Our framework, termed Vision ARC (VARC), achieves 60.4% accuracy on the ARC-1 benchmark, substantially outperforming existing methods that are also trained from scratch. Our results are competitive with those of leading LLMs and close the gap to average human performance.