Visual Access Boundaries in Vision-Language Model Reasoning

Jul 15, 2026

A new preprint introduces Visual Access Sweep, a causal intervention technique to study how Vision-Language Models (VLMs) use image information during Chain-of-Thought (CoT) reasoning. The study finds that VLMs do not require ongoing access to image tokens throughout CoT reasoning; instead, CoT mainly extends language-side computation over previously extracted image-derived hidden states. The research also shows that the effectiveness of CoT is limited by the model's ability to reliably read out perceptual attributes, rather than by its counting ability.

Why it matters: This work challenges common assumptions about CoT in VLMs and suggests that improving perceptual readout, rather than extending visual access, may be key to further performance gains.

Full story at: arXiv AI/ML ↗