arXiv cs.AI· Xinyu Deng, Siwen Luo, Daochang Liu·· 13 小时前AI 评分31
视频理解智能体综述：从固定推理到主动决策的系统梳理
Agentic Video Understanding: A Survey
AI 导读
一篇被 DICTA 2026 接收的综述系统梳理了视频理解智能体——以视频为主要信息源、通过自适应状态构建与动作选择完成理解任务的系统。文章形式化定义了视频理解的智能体循环，并用“挑战到设计”的分类法把上下文瓶颈、证据稀疏、时序因果和多模态歧义分别对应到分层证据记忆、主动证据获取、状态与过程跟踪、角色专门化协作。
正文 · 原文
Abstract:As large language models (LLMs) become capable of processing increasingly diverse modalities and longer temporal contexts, an emerging line of work is moving beyond fixed video-language inference toward agentic systems that actively decide what information to inspect, retain, verify, and act upon. This survey reviews video understanding agents: systems that use video as the primary information source and solve understanding tasks through adaptive state construction and action selection. We first formalize an agent loop for video understanding, then address a central question: why do agents matter for video understanding? To answer this, we organize the literature through a challenge-to-design taxonomy, linking context bottlenecks to hierarchical evidence memory, evidence sparsity to active evidence acquisition, temporal causality to state and process tracking, and multimodal ambiguity to role-specialized coordination. We further review state space paradigms, learning paradigms, supervision signals, benchmarks, and evaluation protocols. Finally, we identify open directions toward agentic-native temporal modeling and video-native agents. Project page: this https URL
| Comments: | 15 pages,3 figures, Accepted to DICTA 2026; Revised Fig. 2 to correct taxonomy inconsistencies |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2609.31713 [cs.CV] |
| (or arXiv:2609.31713v2 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2609.31713 arXiv-issued DOI via DataCite |
Submission history
From: Xinyu Deng [view email]
[v1]
Mon, 21 Sep 2026 02:58:10 UTC (5,033 KB)
[v2]
Wed, 21 Oct 2026 02:49:27 UTC (5,031 KB)
来源：arXiv cs.AI · arxiv.org