In real-world video question answering scenarios, videos often provide only localized visual cues, while verifiable answers are distributed across the open web; models therefore need to jointly perform cross-frame clue extraction, iterative retrieval, and multi-hop reasoning-based verification. To bridge this gap, we construct the first video deep research benchmark, VideoDR. VideoDR centers on video-conditioned open-domain video question answering, requiring cross-frame visual anchor extraction, interactive web retrieval, and multi-hop reasoning over joint video-web evidence; through rigorous human annotation and quality control, we obtain high-quality video deep research samples spanning six semantic domains. We evaluate multiple closed-source and open-source multimodal large language models under both the Workflow and Agentic paradigms, and the results show that Agentic is not consistently superior to Workflow: its gains depend on a model's ability to maintain the initial video anchors over long retrieval chains. Further analysis indicates that goal drift and long-horizon consistency are the core bottlenecks. In sum, VideoDR provides a systematic benchmark for studying video agents in open-web settings and reveals the key challenges for next-generation video deep research agents.

翻译：在现实世界的视频问答场景中，视频通常仅提供局部视觉线索，而可验证的答案则分布在开放网络上；因此，模型需要联合执行跨帧线索提取、迭代检索以及基于多跳推理的验证。为弥补这一差距，我们构建了首个视频深度研究基准——VideoDR。VideoDR以视频为条件的开放域视频问答为核心，要求进行跨帧视觉锚点提取、交互式网络检索，以及对联合视频-网络证据的多跳推理；通过严格的人工标注与质量控制，我们获得了涵盖六个语义领域的高质量视频深度研究样本。我们在工作流范式与智能体范式下评估了多个闭源与开源的多模态大语言模型，结果表明，智能体范式并非始终优于工作流范式：其优势取决于模型在长检索链中保持初始视频锚点的能力。进一步分析表明，目标漂移与长程一致性是核心瓶颈。总之，VideoDR为研究开放网络环境下的视频智能体提供了一个系统性基准，并揭示了下一代视频深度研究智能体所面临的关键挑战。