# TraceViT: Grounded Trace Supervision for Visual Abstract Reasoning

arXiv: https://arxiv.org/abs/2607.29586 · HTML: https://mlsanity.com/paper/2607.29586/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 37 references that are in the map.
- First posted on arXiv 31 Jul 2026.

## Builds on (most cited first, 23 of 23)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Object-Centric Learning with Slot Attention](https://mlsanity.com/paper/2006.15055/) (2020)
- [Soft-DTW: a Differentiable Loss Function for Time-Series](https://mlsanity.com/paper/1703.01541/) (2017)
- [LLMs and the Abstraction and Reasoning Corpus: Successes, Failures, and the Importance of Object-based Representations](https://mlsanity.com/paper/2305.18354/) (2023)
- [Improving Object-centric Learning with Query Optimization](https://mlsanity.com/paper/2210.08990/) (2022)
- [Combining Induction and Transduction for Abstract Reasoning](https://mlsanity.com/paper/2411.02272/) (2024)
- [Self-Improving Language Models for Evolutionary Program Synthesis: A Case Study on ARC-AGI](https://mlsanity.com/paper/2507.14172/) (2025)
- [Graphs, Constraints, and Search for the Abstraction and Reasoning Corpus](https://mlsanity.com/paper/2210.09880/) (2022)
- [Neural-guided, Bidirectional Program Search for Abstraction and Reasoning](https://mlsanity.com/paper/2110.11536/) (2021)
- [Product of Experts with LLMs: Boosting Performance on ARC Is a Matter of Perspective](https://mlsanity.com/paper/2505.07859/) (2025)
- [LoopViT: Scaling Visual ARC with Looped Transformers](https://mlsanity.com/paper/2602.02156/) (2026)
- [Slot Abstractors: Toward Scalable Abstract Visual Reasoning](https://mlsanity.com/paper/2403.03458/) (2024)
- [Towards Efficient Neurally-Guided Program Induction for ARC-AGI](https://mlsanity.com/paper/2411.17708/) (2024)
- [Generalized Planning for the Abstraction and Reasoning Corpus](https://mlsanity.com/paper/2401.07426/) (2024)
- [Tackling the Abstraction and Reasoning Corpus with Vision Transformers: the Importance of 2D Representation, Positions, and Objects](https://mlsanity.com/paper/2410.06405/) (2024)
- [ARC-GEN: A Mimetic Procedural Benchmark Generator for the Abstraction and Reasoning Corpus](https://mlsanity.com/paper/2511.00162/) (2025)
- [ConceptSearch: Towards Efficient Program Search Using LLMs for Abstraction and Reasoning Corpus (ARC)](https://mlsanity.com/paper/2412.07322/) (2024)
- [Tackling the Abstraction and Reasoning Corpus (ARC) with Object-centric Models and the MDL Principle](https://mlsanity.com/paper/2311.00545/) (2023)
- [Don't throw the baby out with the bathwater: How and why deep learning for ARC](https://mlsanity.com/paper/2506.14276/) (2025)
- [Tiny Recursive Reasoning with Mamba-2 Attention Hybrid](https://mlsanity.com/paper/2602.12078/) (2026)
- [Test-time Adaptation of Tiny Recursive Models](https://mlsanity.com/paper/2511.02886/) (2025)
- [Slots, Transitions, Loops: Learning Composable World Models for ARC](https://mlsanity.com/paper/2606.12316/) (2026)
- [ARCTraj: A Dataset and Benchmark of Human Reasoning Trajectories for Abstract Problem Solving](https://mlsanity.com/paper/2511.11079/) (2025)

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

- [Few-Shot Demonstrations Elicit the Use of In-Context World Representations in LLMs](https://mlsanity.com/paper/2609.24352/) (2026)

## Abstract (arXiv)

The Abstraction and Reasoning Corpus (ARC) tests whether a model can infer an unseen transformation from a few input-output examples and apply it to a new grid. Looped visual reasoners refine predictions over multiple iterations, but conventional training constrains only the final output, leaving intermediate refinements unconstrained. We propose that these refinements should instead follow the transformation step by step. We introduce TraceViT, a looped visual reasoner trained with semantically monotonic transformation chains. We obtain these chains by rewriting and verifying programmatic task implementations, decomposing each solution into intermediate grid states. Each iteration is grounded by a task reference derived from the few-shot demonstrations and an object workspace representing the current grid state. Because these chains may differ in length from the loop, soft trace alignment enforces only their ordering, letting the model allocate iterations freely. TraceViT achieves 67.8% pass@2 on ARC-AGI-1 and 24.3% on ARC-AGI-2. Controlled ablations on ARC-AGI-1 show that trace supervision becomes beneficial only when paired with grounding. Code and data will be available at https://github.com/LiuBinnan/TraceViT.