arXiv cs.CL· Jiahao Meng, Qize Yang, Yuxuan Wang, Yunfei Chu, Wensi Dai, Jin Xu, Yunhai Tong·· 13 小时前AI 评分29
超越观看与搜索：以视频为中心的深度研究报告智能体基准测试
Beyond Watching and Searching: Benchmarking Agents for Video-centered Deep Research Reports
AI 导读
研究提出以视频为中心的深度研究报告生成任务，并发布 OmniDR-Bench 基准，包含 50 个中英文任务、覆盖 19 个真实子类，共 6,414 条评估标准。配套的 Omni-ARTs 评估体系从视听 grounding、多模态证据使用和交互呈现三个维度打分，18 种智能体配置中最佳系统仅得 63.3 分。现有智能体在内容覆盖广度、跨模态因果逻辑分析和引用准确性上仍有明显不足。
正文 · 原文
Abstract:Deep research agents synthesize open-web evidence into long reports, but current benchmarks do not evaluate research centered on a source video. We introduce Video-Centered Deep Research Report Generation. Given a video and user request, an agent identifies research questions, retrieves external multimodal evidence, and produces an interactive report linked to relevant video moments. This task has direct practical value because it helps users locate relevant moments, verify claims, reproduce demonstrated procedures, and make informed decisions from video content. We present a skill-based workflow and OmniDR-Bench for this task. For evaluation, we propose Omni Atomic Rubric Trees (Omni-ARTs). Each tree contains three dimensions, 23 shared directions, and task-specific atomic binary criteria. The directions test audiovisual grounding, multimodal evidence use, and interactive presentation. Audited Rubric Construction (ARC) builds these trees through independent evidence collection, automated checks, behavioral calibration, and iterative human review. OmniDR-Bench contains 50 Chinese and English tasks across 19 realworld subcategories. It includes 6,414 criteria. Across 18 agent configurations, the best system scores 63.3 out of 100. Current agents still need broader content coverage, stronger causal and logical analysis across modalities, and more accurate citation support. We further analyze models, harnesses, skill configurations, video categories, and research trajectories. The code and data are released at this https URL.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.31158 [cs.CV] |
| (or arXiv:2610.31158v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.31158 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Jiahao Meng [view email]
[v1]
Thu, 22 Oct 2026 12:15:30 UTC (9,444 KB)
来源：arXiv cs.CL · arxiv.org