When thinking with images, humans rarely rely on a single glance: they revisit visual evidence while reasoning. In contrast, most Multimodal Language Models encode an image once to key-value cache and then reason purely in text, making it hard to re-ground intermediate steps. We empirically confirm this: as reasoning chains lengthen, models progressively lose focus on relevant regions. We introduce v1, a lightweight extension for active visual referencing via point-and-copy: the model selects relevant image patches and copies their embeddings back into the reasoning stream. Crucially, our point-and-copy mechanism retrieves patches using their semantic representations as keys, ensuring perceptual evidence remains aligned with the reasoning space. To train this behavior, we build v1, a dataset of 300K multimodal reasoning traces with interleaved grounding annotations. Across multimodal mathematical reasoning benchmarks, v1 consistently outperforms comparable baselines. We plan to release the model checkpoint and data.

翻译：人类在借助图像思考时，很少仅依赖单次扫视：他们会在推理过程中反复审视视觉证据。相比之下，大多数多模态语言模型将图像一次性编码为键值缓存，随后仅进行纯文本推理，这使得在中间步骤中重新接地变得困难。我们通过实证证实了这一点：随着推理链的延长，模型逐渐失去对相关区域的关注。我们提出了v1，一种通过指向-复制机制实现主动视觉引用的轻量级扩展：模型选择相关的图像块，并将其嵌入向量复制回推理流中。关键在于，我们的指向-复制机制使用图像块的语义表示作为键来检索它们，确保感知证据始终与推理空间对齐。为了训练这一行为，我们构建了v1数据集，包含30万条带有交错接地标注的多模态推理轨迹。在多个多模态数学推理基准测试中，v1持续优于可比基线。我们计划发布模型检查点和数据。