# Pretraining and Test-Time Training Budgets Matter for ARC: A Controlled Study of VARC and TRM

arXiv: https://arxiv.org/abs/2610.13660 · HTML: https://mlsanity.com/paper/2610.13660/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 26 references that are in the map.
- First posted on arXiv 9 Oct 2026.

## Builds on (most cited first, 16 of 16)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [ARC-AGI-2: A New Challenge for Frontier AI Reasoning Systems](https://mlsanity.com/paper/2505.11831/) (2025)
- [The ConceptARC Benchmark: Evaluating Understanding and Generalization in the ARC Domain](https://mlsanity.com/paper/2305.07141/) (2023)
- [The Surprising Effectiveness of Test-Time Training for Few-Shot Learning](https://mlsanity.com/paper/2411.07279/) (2024)
- [LLMs and the Abstraction and Reasoning Corpus: Successes, Failures, and the Importance of Object-based Representations](https://mlsanity.com/paper/2305.18354/) (2023)
- [Addressing the Abstraction and Reasoning Corpus via Procedural Example Generation](https://mlsanity.com/paper/2404.07353/) (2024)
- [Fixed-Point Reasoners: Stable and Adaptive Deep Looped Transformers](https://mlsanity.com/paper/2606.18206/) (2026)
- [ARC Is a Vision Problem!](https://mlsanity.com/paper/2511.14761/) (2025)
- [LoopViT: Scaling Visual ARC with Looped Transformers](https://mlsanity.com/paper/2602.02156/) (2026)
- [Tackling the Abstraction and Reasoning Corpus with Vision Transformers: the Importance of 2D Representation, Positions, and Objects](https://mlsanity.com/paper/2410.06405/) (2024)
- [Tackling the Abstraction and Reasoning Corpus (ARC) with Object-centric Models and the MDL Principle](https://mlsanity.com/paper/2311.00545/) (2023)
- [Compositional-ARC: Assessing Systematic Generalization in Abstract Spatial Reasoning](https://mlsanity.com/paper/2504.01445/) (2025)
- [Bongards at the Boundary of Perception and Reasoning: Programs or Language?](https://mlsanity.com/paper/2602.03038/) (2026)
- [Implicit Rule Induction with Test-Time Task Embeddings in ARC-like Tasks](https://mlsanity.com/paper/2609.21181/) (2026)
- [PotARCin: Multi-Dimensional Evaluation of Skill Acquisition in Abstract Reasoning Tasks](https://mlsanity.com/paper/2609.27288/) (2026)

## Abstract (arXiv)

The Abstraction and Reasoning Corpus (ARC) is increasingly used to evaluate whether neural networks can infer task-specific transformations from few demonstrations. Recent ARC models differ in architecture, but also in broader training and evaluation protocols, including pretraining data, data augmentation, test-time setup, and optimization budgets, making conclusions about architecture benefits debatable. In this work, we study how the performance of the vision-inspired VARC and recursion-based TRM models is affected by pretraining and test-time training (TTT) budgets under a common inductive protocol on ARC-AGI-1. We cross five pretraining budgets with four TTT budgets for each test task. Each budget specifies a task-variant count and total sample presentations, defining the controlled training budgets. We observe that increasing TTT sample presentations improves the standard ARC pass@2 metric in all settings for both models. Increasing the TTT task-variant count consistently helps only TRM, whereas VARC often performs better with fewer variants. VARC also remains competitive without pretraining, while TRM benefits much more from it. These results show that pretraining and TTT budgets affect ARC evaluation and motivate reporting at comparable budgets.