arXiv 2610.31158 · cs.CV · 2026-10-22
Beyond Watching and Searching: Benchmarking Agents for Video-centered Deep Research Reports
Jiahao Meng, Qize Yang, Yuxuan Wang, Yunfei Chu, Wensi Dai, Jin Xu, Yunhai Tong
Qwen
在最新榜 #280 本站收录于 2026-10-25
一句话要点
通义千问提出以视频为中心的深度研究报告任务和 OmniDR-Bench：agent 根据视频和需求找问题、检索多模态证据，生成链接到视频片段的交互式报告，并用 Omni-ARTs 评分。
Qwen introduces video-centered deep research report generation and OmniDR-Bench, where agents retrieve multimodal evidence and produce interactive reports linked to video moments, scored with Omni Atomic Rubric Trees.
阅读 arXiv 原文 PDF Hugging Face 讨论 代码仓库
主题与学科
同主题：智能体
- Raven: The Harness of Harnesses for Composable Agentic Intelligence ▲748
- False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents ▲642
- Omni-IO Skills: Harnessing Your Agent Omni-Native ▲485
- BizAgentBench: Unveiling Hidden Challenges in Deploying Long-Horizon Agents for Real-World Business ▲388
- Player-1: Learning to Play from Synthetic Experience ▲347
同主题：多模态
- StreamEval: Evaluating Interactive Streaming Video Generation Models 2026-10-20 · ▲649
- MJev-Spatial: System One Spatial Intelligence via Native Attention Matching 2026-10-15 · ▲556
- LoopVL: Recurrent Visual Intelligence 2026-09-29 · ▲417
- VideoJev: System One Model for Video Understanding and Interaction 2026-10-13 · ▲375
- S-Space: Exploring Spatial Workspace in Multimodal Language Models 2026-10-09 · ▲270
同机构：Qwen
- BlenderWorld: Benchmarking Visual Agents for 3D Creation from Real-World References 2026-10-14
- Last Secure Code Benchmark: Is the Code You Vibe Secure? 2026-10-10
- TRACE: Rollout-Guided Quantization-Aware Training for FP4 Reinforcement Learning of MoE Language Models 2026-10-06
- VisionWeave: Weaving Elastic Visual Representations as a Native Capability of MLLMs 2026-10-06
- OmniVChat: Synthesizing, Benchmarking, and Training for Native Audio-Visual Dialogue 2026-09-18
数据说明
元数据来自 arXiv API（已核实）；点赞来自 Hugging Face 每日论文；引用来自 Semantic Scholar。最近刷新 2026-10-26。
要点由本站根据摘要自写，不转载摘要原文，请阅读原文。