这篇论文用实验告诉你，视觉语言模型做CoT推理时，图像其实只在开头看一次，后面全靠语言处理。想知道为什么CoT有时没用？进来看看
论文提出Visual Access Sweep方法，通过遮蔽生成token到图像token的注意力，定义Visual Access Boundary (VAB)。在Qwen2.5-VL-32B和InternVL3的14B、38B规模上，CoT的VAB层与无CoT全访问目标差异最多两层。CoT提升受限于感知读出：当视觉属性可可靠读出时CoT有效，否则无效。符号属性oracle显示，提供真实属性文本后CoT可改善计数。单目标探针-解码检查表明，困难属性可从隐藏状态线性恢复但模型难以输出。
Visual Access Boundaries in Vision-Language Model Reasoning
Chain-of-Thought (CoT) prompting is widely used as a test-time scaling strategy for Vision-Language Models (VLMs), but it remains unclear what is extended when VLMs generate longer reasoning traces. We ask whether CoT requires continued access to image tokens, or whether it mainly operates over visual information already made available earlier in the forward pass. We introduce Visual Access Sweep, a causal intervention that masks attention from generated-token queries to image-token keys along layer depth and generation time, and define the Visual Access Boundary (VAB) as the minimal access region that preserves task accuracy. Across six model configurations from Qwen2.5-VL and InternVL3, both no-CoT direct answering and CoT prompting exhibit finite VABs. In Qwen2.5-VL-32B and InternVL3 at 14B and 38B scales, when CoT is evaluated against the no-CoT full-access target, its VAB layer differs from the no-CoT boundary by at most two layers, despite substantially longer generations. This suggests that CoT does not primarily improve performance by prolonging direct image-token access throughout the reasoning trace, but by extending language-side computation over image-derived hidden-state information. We further show that CoT gains are constrained by perceptual readout. CoT helps when the queried visual attribute can be reliably read out by the model, but not when that readout is unreliable. A symbolic-attribute oracle shows that CoT can improve counting once ground-truth attributes are supplied as text, while a single-object probe-vs-decode check shows that hard attributes can be linearly recoverable from hidden states yet difficult for the model itself to output. Together, these analyses place the bottleneck at readout rather than counting.