paper-with-me

홈 › Papers

Reasoning via Video: The First Evaluation of Video Models' Reasoning Abilities through Maze-Solving Tasks

2025-11-19 · Cheng Yang, Haiyuan Wan, Yiran Peng, Xin Cheng, Zhaoyang Yu, Jiayi Zhang, Junchi Yu, Xinlei Yu, Xiawu Zheng, Dongzhan Zhou, Chenglin Wu arxiv

Video Models have achieved remarkable success in high-fidelity video generation with coherent motion dynamics. Analogous to the development from text generation to text-based reasoning in language modeling, the development of video models motivates us to ask: Can video models reason via video generation? Compared with the discrete text corpus, video grounds reasoning in explicit spatial layouts and temporal continuity, which serves as an ideal substrate for spatial reasoning. In this work, we explore the reasoning via video paradigm and introduce VR-Bench -- a comprehensive benchmark designed to systematically evaluate video models' reasoning capabilities. Grounded in maze-solving tasks that inherently require spatial planning and multi-step reasoning, VR-Bench contains 7,920 procedurally generated videos across five maze types and diverse visual styles. Our empirical analysis demonstrates that SFT can efficiently elicit the reasoning ability of video model. Video models exhibit stronger spatial perception during reasoning, outperforming leading VLMs and generalizing well across diverse scenarios, tasks, and levels of complexity. We further discover a test-time scaling effect, where diverse sampling during inference improves reasoning reliability by 10--20%. These findings highlight the unique potential and scalability of reasoning via video for spatial reasoning tasks.

📄 PDF Abstract BibTeX arXiv:2511.15065

Code (0)

등록된 구현이 없습니다.

Tasks

Spatial ReasoningVideo GenerationText Generation

Similar Papers 제목 키워드 기반

VideoSeg-R1:Reasoning Video Object Segmentation via Reinforcement Learning

2025-11-20 · Zishan Xu, Yifu Guo, Yuquan Lu, Fengyu Yang 외 arxiv

Traditional video reasoning segmentation methods rely on supervised fine-tuning, which limits generalization to out-of-distribution scenarios and lacks explicit reasoning. To address this, we propose \textbf{VideoSeg-R1}…

Video Object SegmentationReinforcement LearningImage Segmentation

A Very Big Video Reasoning Suite

2026-02-23 · Maijunxian Wang, Ruisi Wang, Juyi Lin, Ran Ji 외 arxiv

Rapid progress in video models has largely focused on visual quality, leaving their reasoning capabilities underexplored. Video reasoning grounds intelligence in spatiotemporally consistent visual environments that go be…

Commonsense Video Question Answering through Video-Grounded Entailment Tree Reasoning

2025-01-09 · CVPR 2025 1 · Huabin Liu, Filip Ilievski, Cees G. M. Snoek

This paper proposes the first video-grounded entailment tree reasoning method for commonsense video question answering (VQA). Despite the remarkable progress of large visual-language models (VLMs), there are growing conc…

BenchmarkingQuestion AnsweringVideo Question AnsweringVisual Question Answering (VQA)

MME-CoF-Pro: Evaluating Reasoning Coherence in Video Generative Models with Text and Visual Hints

2026-03-20 · Yu Qi, Xinyi Xu, Ziyu Guo, Siyuan Ma 외 arxiv

Video generative models show emerging reasoning behaviors. It is essential to ensure that generated events remain causally consistent across frames for reliable deployment, a property we define as reasoning coherence. To…

Coherence Evaluation

V-STaR: Benchmarking Video-LLMs on Video Spatio-Temporal Reasoning

2025-03-14 · Zixu Cheng, Jian Hu, Ziquan Liu, Chenyang Si 외

Human processes video reasoning in a sequential spatio-temporal reasoning logic, we first identify the relevant frames ("when") and then analyse the spatial relationships ("where") between key objects, and finally levera…

BenchmarkingRelational ReasoningVideo Understanding