VideoAuto-R1: Video Auto Reasoning via Thinking Once, Answering Twice
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914412694077440 |
|---|---|
| author | Liu, Shuming Zhuge, Mingchen Zhao, Changsheng Chen, Jun Wu, Lemeng Liu, Zechun Zhu, Chenchen Cai, Zhipeng Zhou, Chong Liu, Haozhe Chang, Ernie Suri, Saksham Xu, Hongyu Qian, Qi Wen, Wei Varadarajan, Balakrishnan Liu, Zhuang Xu, Hu Bordes, Florian Krishnamoorthi, Raghuraman Ghanem, Bernard Chandra, Vikas Xiong, Yunyang |
| author_facet | Liu, Shuming Zhuge, Mingchen Zhao, Changsheng Chen, Jun Wu, Lemeng Liu, Zechun Zhu, Chenchen Cai, Zhipeng Zhou, Chong Liu, Haozhe Chang, Ernie Suri, Saksham Xu, Hongyu Qian, Qi Wen, Wei Varadarajan, Balakrishnan Liu, Zhuang Xu, Hu Bordes, Florian Krishnamoorthi, Raghuraman Ghanem, Bernard Chandra, Vikas Xiong, Yunyang |
| contents | Chain-of-thought (CoT) reasoning has emerged as a powerful tool for multimodal large language models on video understanding tasks. However, its necessity and advantages over direct answering remain underexplored. In this paper, we first demonstrate that for RL-trained video models, direct answering often matches or even surpasses CoT performance, despite CoT producing step-by-step analyses at a higher computational cost. Motivated by this, we propose VideoAuto-R1, a video understanding framework that adopts a reason-when-necessary strategy. During training, our approach follows a Thinking Once, Answering Twice paradigm: the model first generates an initial answer, then performs reasoning, and finally outputs a reviewed answer. Both answers are supervised via verifiable rewards. During inference, the model uses the confidence score of the initial answer to determine whether to proceed with reasoning. Across video QA and grounding benchmarks, VideoAuto-R1 achieves state-of-the-art accuracy with significantly improved efficiency, reducing the average response length by ~3.3x, e.g., from 149 to just 44 tokens. Moreover, we observe a low rate of thinking-mode activation on perception-oriented tasks, but a higher rate on reasoning-intensive tasks. This suggests that explicit language-based reasoning is generally beneficial but not always necessary. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_05175 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | VideoAuto-R1: Video Auto Reasoning via Thinking Once, Answering Twice Liu, Shuming Zhuge, Mingchen Zhao, Changsheng Chen, Jun Wu, Lemeng Liu, Zechun Zhu, Chenchen Cai, Zhipeng Zhou, Chong Liu, Haozhe Chang, Ernie Suri, Saksham Xu, Hongyu Qian, Qi Wen, Wei Varadarajan, Balakrishnan Liu, Zhuang Xu, Hu Bordes, Florian Krishnamoorthi, Raghuraman Ghanem, Bernard Chandra, Vikas Xiong, Yunyang Computer Vision and Pattern Recognition Chain-of-thought (CoT) reasoning has emerged as a powerful tool for multimodal large language models on video understanding tasks. However, its necessity and advantages over direct answering remain underexplored. In this paper, we first demonstrate that for RL-trained video models, direct answering often matches or even surpasses CoT performance, despite CoT producing step-by-step analyses at a higher computational cost. Motivated by this, we propose VideoAuto-R1, a video understanding framework that adopts a reason-when-necessary strategy. During training, our approach follows a Thinking Once, Answering Twice paradigm: the model first generates an initial answer, then performs reasoning, and finally outputs a reviewed answer. Both answers are supervised via verifiable rewards. During inference, the model uses the confidence score of the initial answer to determine whether to proceed with reasoning. Across video QA and grounding benchmarks, VideoAuto-R1 achieves state-of-the-art accuracy with significantly improved efficiency, reducing the average response length by ~3.3x, e.g., from 149 to just 44 tokens. Moreover, we observe a low rate of thinking-mode activation on perception-oriented tasks, but a higher rate on reasoning-intensive tasks. This suggests that explicit language-based reasoning is generally beneficial but not always necessary. |
| title | VideoAuto-R1: Video Auto Reasoning via Thinking Once, Answering Twice |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2601.05175 |