TraceViT在ARC上刷到67.8%，思路是让每步推理都有中间状态监督，代码还会开源，想搞视觉推理的可以盯一下。
ARC基准要求模型从少量输入输出样例推断变换并应用到新网格。TraceViT是一个循环视觉推理器，训练时通过程序实现改写生成中间网格状态，使每步迭代都对齐任务参考和对象工作区。在ARC-AGI-1上达到67.8% pass@2，在ARC-AGI-2上达到24.3%。消融实验显示，轨迹监督只有在配合grounding时才有收益。
TraceViT: Grounded Trace Supervision for Visual Abstract Reasoning
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.