We\u2019ve spent years teaching AI to reason better. First came chain-of-thought prompting, which let language models talk through their logic step-by-step instead of jumping straight to answers. Then came vision language models, which grounded reasoning in actual images. Both worked. Both improved the numbers.But there\u2019s a fundamental problem nobody talks about: these approaches reach a wall, and the wall is time.Text reasoning can describe a process step-by-step, but it\u2019s abstract. When you ask an AI to solve a geometry puzzle or verify a mechanical process, explaining it in words feels clumsy. You\u2019re describing spatial relationships with tokens.Images, meanwhile, are frozen moments. A single photograph of water halfway filling a glass conveys something, sure, but it\u2019s not the same as a video of water being poured. Many real reasoning tasks are inherently temporal or spatial in ways that demand motion: drawing shapes to verify geometry, animating a mechanical process to check if it works, simulating a step-by-step transformation to find a pattern. Static frames fail to capture the essence of how one state becomes another.And then there\u2019s the deeper architectural problem: text and vision stay in separate lanes. Current systems either think with text about images, or think with images about text. They\u2019re dual systems pretending to be unified. There\u2019s no natural way for visual reasoning to flow into textual reasoning or vice versa.This paper asks a simple but radical question: what if we let AI models generate videos to think through problems? Not to communicate answers, but to actually reason. Let the model externalize its thinking process into motion. The answer reveals something surprising: video might not just be a richer format, it might be the key to unified multimodal reasoning.What video thinking actually meansBefore diving into results, the mechanism itself needs clarification. What does it actually mean to \u201creason by generating video\u201d?Think of it as giving an AI a way to externalize its internal reasoning process. Instead of computing an answer silently and outputting text, the model \u201cthinks out loud\u201d by generating a sequence of images. The video is the reasoning. When you ask it to solve a puzzle, it animates the solution step-by-step. When you ask it to find a pattern, it generates frames that show the transformation unfolding.The key insight is that modern video generation models like Sora-2 are trained to generate plausible sequences of images that follow physical and logical rules. This constraint on coherence between frames, \u201cwhat you generate in frame N should lead sensibly to frame N+1,\u201d is actually a strong signal for reasoning. It\u2019s a built-in consistency check that text reasoning doesn\u2019t have.<\/p>\n
Read more<\/p>\n","protected":false},"excerpt":{"rendered":"