VideoAgent2: Enhancing the LLM-Based Agent System for Long-Form Video Understanding by Uncertainty-Aware CoT
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917978734329856 |
|---|---|
| author | Zhi, Zhuo Wu, Qiangqiang shen, Minghe Li, Wenbo Li, Yinchuan Shao, Kun Zhou, Kaiwen |
| author_facet | Zhi, Zhuo Wu, Qiangqiang shen, Minghe Li, Wenbo Li, Yinchuan Shao, Kun Zhou, Kaiwen |
| contents | Long video understanding has emerged as an increasingly important yet challenging task in computer vision. Agent-based approaches are gaining popularity for processing long videos, as they can handle extended sequences and integrate various tools to capture fine-grained information. However, existing methods still face several challenges: (1) they often rely solely on the reasoning ability of large language models (LLMs) without dedicated mechanisms to enhance reasoning in long video scenarios; and (2) they remain vulnerable to errors or noise from external tools. To address these issues, we propose a specialized chain-of-thought (CoT) process tailored for long video analysis. Our proposed CoT with plan-adjust mode enables the LLM to incrementally plan and adapt its information-gathering strategy. We further incorporate heuristic uncertainty estimation of both the LLM and external tools to guide the CoT process. This allows the LLM to assess the reliability of newly collected information, refine its collection strategy, and make more robust decisions when synthesizing final answers. Empirical experiments show that our uncertainty-aware CoT effectively mitigates noise from external tools, leading to more reliable outputs. We implement our approach in a system called VideoAgent2, which also includes additional modules such as general context acquisition and specialized tool design. Evaluation on three dedicated long video benchmarks (and their subsets) demonstrates that VideoAgent2 outperforms the previous state-of-the-art agent-based method, VideoAgent, by an average of 13.1% and achieves leading performance among all zero-shot approaches |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_04471 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | VideoAgent2: Enhancing the LLM-Based Agent System for Long-Form Video Understanding by Uncertainty-Aware CoT Zhi, Zhuo Wu, Qiangqiang shen, Minghe Li, Wenbo Li, Yinchuan Shao, Kun Zhou, Kaiwen Computer Vision and Pattern Recognition Long video understanding has emerged as an increasingly important yet challenging task in computer vision. Agent-based approaches are gaining popularity for processing long videos, as they can handle extended sequences and integrate various tools to capture fine-grained information. However, existing methods still face several challenges: (1) they often rely solely on the reasoning ability of large language models (LLMs) without dedicated mechanisms to enhance reasoning in long video scenarios; and (2) they remain vulnerable to errors or noise from external tools. To address these issues, we propose a specialized chain-of-thought (CoT) process tailored for long video analysis. Our proposed CoT with plan-adjust mode enables the LLM to incrementally plan and adapt its information-gathering strategy. We further incorporate heuristic uncertainty estimation of both the LLM and external tools to guide the CoT process. This allows the LLM to assess the reliability of newly collected information, refine its collection strategy, and make more robust decisions when synthesizing final answers. Empirical experiments show that our uncertainty-aware CoT effectively mitigates noise from external tools, leading to more reliable outputs. We implement our approach in a system called VideoAgent2, which also includes additional modules such as general context acquisition and specialized tool design. Evaluation on three dedicated long video benchmarks (and their subsets) demonstrates that VideoAgent2 outperforms the previous state-of-the-art agent-based method, VideoAgent, by an average of 13.1% and achieves leading performance among all zero-shot approaches |
| title | VideoAgent2: Enhancing the LLM-Based Agent System for Long-Form Video Understanding by Uncertainty-Aware CoT |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.04471 |