Guardado en:
| Autores principales: | , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2511.15065 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909919281676288 |
|---|---|
| author | Yang, Cheng Wan, Haiyuan Peng, Yiran Cheng, Xin Yu, Zhaoyang Zhang, Jiayi Yu, Junchi Yu, Xinlei Zheng, Xiawu Zhou, Dongzhan Wu, Chenglin |
| author_facet | Yang, Cheng Wan, Haiyuan Peng, Yiran Cheng, Xin Yu, Zhaoyang Zhang, Jiayi Yu, Junchi Yu, Xinlei Zheng, Xiawu Zhou, Dongzhan Wu, Chenglin |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_15065 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Reasoning via Video: The First Evaluation of Video Models' Reasoning Abilities through Maze-Solving Tasks Yang, Cheng Wan, Haiyuan Peng, Yiran Cheng, Xin Yu, Zhaoyang Zhang, Jiayi Yu, Junchi Yu, Xinlei Zheng, Xiawu Zhou, Dongzhan Wu, Chenglin Computer Vision and Pattern Recognition Artificial Intelligence 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. |
| title | Reasoning via Video: The First Evaluation of Video Models' Reasoning Abilities through Maze-Solving Tasks |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2511.15065 |