Recent advances in visual reasoning have leveraged vision transformers to tackle the ARC-AGI benchmark. However, we argue that the feed-forward architecture, where computational depth is strictly bound to parameter size, falls short of capturing the iterative, algorithmic nature of human induction. In this work, we propose a recursive architecture called Loop-ViT, which decouples reasoning depth from model capacity through weight-tied recurrence. Loop-ViT iterates a weight-tied Hybrid Block, combining local convolutions and global attention, to form a latent chain of thought. Crucially, we introduce a parameter-free Dynamic Exit mechanism based on predictive entropy: the model halts inference when its internal state ``crystallizes" into a low-uncertainty attractor. Empirical results on the ARC-AGI-1 benchmark validate this perspective: our 18M model achieves 65.8% accuracy, outperforming massive 73M-parameter ensembles. These findings demonstrate that adaptive iterative computation offers a far more efficient scaling axis for visual reasoning than simply increasing network width. The code is available at https://github.com/WenjieShu/LoopViT.

翻译：近期视觉推理领域的进展利用视觉Transformer来处理ARC-AGI基准测试。然而，我们认为前馈架构——其计算深度严格受限于参数量——难以捕捉人类归纳推理的迭代式算法本质。本研究提出一种名为Loop-ViT的递归架构，通过权重绑定的循环机制将推理深度与模型容量解耦。Loop-ViT通过迭代执行权重绑定的混合模块（融合局部卷积与全局注意力）形成潜在的思维链。关键创新在于引入基于预测熵的无参数动态退出机制：当模型内部状态“结晶”为低不确定性的吸引子时，推理过程自动终止。在ARC-AGI-1基准上的实证结果验证了该观点：我们的1800万参数模型达到65.8%准确率，优于7300万参数的大型集成模型。这些发现表明，自适应迭代计算为视觉推理提供了远比单纯增加网络宽度更高效的扩展维度。代码公开于https://github.com/WenjieShu/LoopViT。