Weaver: End-to-End Agentic System Training for Video Interleaved Reasoning
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912881743757312 |
|---|---|
| author | Shi, Yudi Di, Shangzhe Chen, Qirui Wang, Qinian Cai, Jiayin Jiang, Xiaolong Hu, Yao Xie, Weidi |
| author_facet | Shi, Yudi Di, Shangzhe Chen, Qirui Wang, Qinian Cai, Jiayin Jiang, Xiaolong Hu, Yao Xie, Weidi |
| contents | Video reasoning constitutes a comprehensive assessment of a model's capabilities, as it demands robust perceptual and interpretive skills, thereby serving as a means to explore the boundaries of model performance. While recent research has leveraged text-centric Chain-of-Thought reasoning to augment these capabilities, such approaches frequently suffer from representational mismatch and restricted by limited perceptual acuity. To address these limitations, we propose Weaver, a novel, end-to-end trainable multimodal reasoning agentic system. Weaver empowers its policy model to dynamically invoke diverse tools throughout the reasoning process, enabling progressive acquisition of crucial visual cues and construction of authentic multimodal reasoning trajectories. Furthermore, we integrate a reinforcement learning algorithm to allow the system to freely explore strategies for employing and combining these tools with trajectory-free data. Extensive experiments demonstrate that our system, Weaver, enhances performance on several complex video reasoning benchmarks, particularly those involving long videos. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_05829 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Weaver: End-to-End Agentic System Training for Video Interleaved Reasoning Shi, Yudi Di, Shangzhe Chen, Qirui Wang, Qinian Cai, Jiayin Jiang, Xiaolong Hu, Yao Xie, Weidi Computer Vision and Pattern Recognition Video reasoning constitutes a comprehensive assessment of a model's capabilities, as it demands robust perceptual and interpretive skills, thereby serving as a means to explore the boundaries of model performance. While recent research has leveraged text-centric Chain-of-Thought reasoning to augment these capabilities, such approaches frequently suffer from representational mismatch and restricted by limited perceptual acuity. To address these limitations, we propose Weaver, a novel, end-to-end trainable multimodal reasoning agentic system. Weaver empowers its policy model to dynamically invoke diverse tools throughout the reasoning process, enabling progressive acquisition of crucial visual cues and construction of authentic multimodal reasoning trajectories. Furthermore, we integrate a reinforcement learning algorithm to allow the system to freely explore strategies for employing and combining these tools with trajectory-free data. Extensive experiments demonstrate that our system, Weaver, enhances performance on several complex video reasoning benchmarks, particularly those involving long videos. |
| title | Weaver: End-to-End Agentic System Training for Video Interleaved Reasoning |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.05829 |