SVAgent：故事线引导的跨模态多智能体协作长视频理解
SVAgent: Storyline-guided Long Video Understanding via Cross-Modal Multi-Agent Collaboration
把「故事线」作为可迭代演化的中间表示，配合跨模态决策智能体与元智能体做答案对齐，为长视频问答提供了一种无需额外训练、可插拔的多智能体推理框架，可直接迁移到长视频理解与时序推理任务。
原文依据 we propose SVAgent, a storyline-guided cross-modal multi-agent framework for VideoQA
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论视频问答（VideoQA）是一项具有挑战性的任务，需要整合空间、时间与语义信息以捕捉视频序列的复杂动态。尽管近期的进展为视频理解引入了多种方法，但大多数现有方法仍依赖定位相关帧来回答问题，而非像人类那样沿着不断演化的故事线进行推理。人类天然地通过连贯的故事线来理解视频，这种能力对于做出鲁棒且具有上下文依据的预测至关重要。为弥补这一差距，我们提出 SVAgent，一个故事线引导的跨模态多智能体视频问答框架。故事线智能体基于由精炼建议智能体所建议的帧，逐步构建叙事表示，而该建议智能体负责分析历史失败案例。此外，跨模态决策智能体在演化中的故事线引导下，分别从视觉与文本模态独立预测答案。随后由一个元智能体对其输出进行评估，以对齐跨模态预测，并增强推理的鲁棒性与答案的一致性。实验结果表明，SVAgent 通过在视频理解中模拟类人的故事线推理，取得了更优的性能与可解释性。
英文原文摘要 1287 字符
Video question answering (VideoQA) is a challenging task that requires integrating spatial, temporal, and semantic information to capture the complex dynamics of video sequences. Although recent advances have introduced various approaches for video understanding, most existing methods still rely on locating relevant frames to answer questions rather than reasoning through the evolving storyline as humans do. Humans naturally interpret videos through coherent storylines, an ability that is crucial for making robust and contextually grounded predictions. To address this gap, we propose SVAgent, a storyline-guided cross-modal multi-agent framework for VideoQA. The storyline agent progressively constructs a narrative representation based on frames suggested by a refinement suggestion agent that analyzes historical failures. In addition, cross-modal decision agents independently predict answers from visual and textual modalities under the guidance of the evolving storyline. Their outputs are then evaluated by a meta-agent to align cross-modal predictions and enhance reasoning robustness and answer consistency. Experimental results demonstrate that SVAgent achieves superior performance and interpretability by emulating human-like storyline reasoning in video understanding.