AI看世界像翻书，不是像人眼
你盯着一个东西看时，眼睛其实在不停跳动、聚焦、根据看到的再调整——这叫主动观察。但现在的AI看一张图，基本就是一次快照。新出的ActiveVision测试专门考这个：17个任务要求模型反复看、根据新发现调整判断。结果最强模型GPT-5.5只答对10.6%，11个任务直接挂零；Claude Fable 5更惨，3.5%，而人类平均96.1%。就算让模型自己写代码去分析图片，代码在真实场景下也不可靠，而发现代码出错本身又需要主动观察——死循环。结论：今天的大模型没有真正的视觉闭环，它不是你明天能用上的，但告诉你为什么AI在需要“边看边想”的事上会翻车。
📄 原文摘要(英文)
Human vision is a closed loop: gaze is continuously redirected by intermediate hypotheses rather than a single snapshot. Decades of psychophysics and cognitive science have argued that this active observation is essential for a wide range of tasks. Whether today's multimodal large language models (MLLMs) exercise active observation is an empirical question that current vision-language benchmarks do not answer. We introduce ActiveVision, a benchmark that makes active observation measurable for MLLMs, comprising 17 tasks across 3 categories. Tasks are designed to force repeated visual perception rather than a single static description. Frontier MLLMs collapse on ActiveVision: the highest-scoring model we evaluate, GPT-5.5 at the highest exposed reasoning-effort tier, solves only 10.6% of items and scores zero on 11 of the 17 tasks, and even Claude Fable 5, despite topping most reasoning and coding leaderboards, solves just 3.5%, far behind three human participants who average 96.1%. Furthermore, much of the gap persists even when models write and run their own vision code: such code is unreliable on realistic imagery, and catching its failures itself requires the active perception the models lack. Together, these results indicate that current MLLMs lack robust active visual observation, motivating architectures and training objectives that close the perception-reasoning loop.