跨模态、跨时间：结构化记忆用于超长代理视频推理
Bridging Modalities, Spanning Time: Structured Memory for Ultra-Long Agentic Video Reasoning
AI总结：
本文提出MAGIC-Video框架，通过多模态记忆图和交织叙事链，实现超长视频的跨模态检索与长时序推理，优于现有基线模型。
摘要：
理解超长视频（如第一视角录像、直播或监控录像）仍具挑战性。现有多模态大语言模型即使有百万token上下文窗口，帧预算仅覆盖几十分钟密集采样视频，大部分证据在推理前被丢弃。记忆增强和代理方法有助于扩展规模，但其检索仍碎片化且缺乏跨天或周的长篇叙事摘要。我们提出MAGIC-Video，一个无需训练的框架，围绕多模态记忆图和交织叙事链：图通过六种类型边统一事件、语义和视觉内容，支持跨模态检索；链提炼长时程实体生物和重复活动事件。在推理时，代理循环交织图检索与叙事事实注入，覆盖超长视频的模态和时间维度。在EgoLifeQA、Ego-R1和MM-Lifelong数据集上，MAGIC-Video在强通用、长视频和代理基线中表现优异，分别优于先前最佳代理系统10.1、7.4和5.9分。代码可在https://github.com/lijiazheng0917/MAGIC-video获取。
英文摘要：
Understanding ultra-long videos such as egocentric recordings, live streams, or surveillance footage spanning days to weeks, remains a challenge. For current multimodal LLMs: even with million-token context windows, frame budgets cover only tens of minutes of densely sampled video, and most evidence is discarded before inference begins. Memory-augmented and agentic approaches help with scale, but their retrieval remains fragmented across modalities and lacks long-range narrative summaries that span days or weeks. We propose \textbf{MAGIC-Video}, a training-free framework built around a multimodal memory graph with interleaved narrative chain: the graph unifies episodic, semantic, and visual content through six typed edges and supports cross-modal retrieval, while the chain distils long-horizon entity biographies and recurring activity events. At inference time, an agentic loop interleaves graph retrieval with narrative fact injection, covering both the modality and time dimensions of ultra-long video in a single retrieval pipeline. On EgoLifeQA, Ego-R1 and MM-Lifelong, MAGIC-Video consistently outperforms strong general-purpose, long-video, and agentic baselines, with gains of 10.1, 7.4, and 5.9 points over the prior best agentic system on each benchmark. Code is available at https://github.com/lijiazheng0917/MAGIC-video.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
