VideoARM：面向长视频理解的分层记忆智能体推理
VideoARM: Agentic Reasoning over Hierarchical Memory for Long-Form Video Understanding
提出一种无需穷举预处理的自适应智能体推理框架，通过控制器调用工具进行由粗到细的视频解析，并维护分层多模态记忆，为长视频理解中的高效多模态大模型推理提供了可复用的记忆构建与工具调度机制。
原文依据 VideoARM performs an adaptive and continuous loop of observing, thinking, acting, and memorizing, where a controller autonomously invokes tools to interpret the video in a coarse-to-fine manner
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论长视频理解由于扩展的时序结构和密集的多模态线索而仍然具有挑战性。尽管近期取得了进展，许多现有方法仍依赖手工设计的推理流程，或采用消耗大量词元的视频预处理来引导多模态大模型进行自主推理。为克服这些局限，我们提出 VideoARM，一种面向长视频理解的分层记忆智能体推理范式。VideoARM 不进行静态、穷举的预处理，而是执行自适应的、即时性的智能体推理与记忆构建。具体而言，VideoARM 执行观察、思考、行动和记忆的自适应连续循环，其中控制器自主调用工具以由粗到细的方式解读视频，从而大幅降低词元消耗。同时，分层多模态记忆在智能体运行过程中持续捕获并更新多级线索，为控制器决策提供精确的上下文信息。在主流基准上的实验表明，VideoARM 优于最优方法 DVD，同时显著降低了长视频的词元消耗。
英文原文摘要 1229 字符
Long-form video understanding remains challenging due to the extended temporal structure and dense multimodal cues. Despite recent progress, many existing approaches still rely on hand-crafted reasoning pipelines or employ token-consuming video preprocessing to guide MLLMs in autonomous reasoning. To overcome these limitations, we introduce VideoARM, an agentic reasoning-over-hierarchical-memory paradigm for long-form video understanding. Instead of static, exhaustive preprocessing, VideoARM performs adaptive, on-the-fly agentic reasoning and memory construction. Specifically, VideoARM performs an adaptive and continuous loop of observing, thinking, acting, and memorizing, where a controller autonomously invokes tools to interpret the video in a coarse-to-fine manner, thereby substantially reducing token consumption. In parallel, a hierarchical multimodal memory continuously captures and updates multi-level clues throughout the operation of the agent, providing precise contextual information to support the controller in decision-making. Experiments on prevalent benchmarks demonstrate that VideoARM outperforms the state-of-the-art method, DVD, while significantly reducing token consumption for long-form videos.