Thinking Beyond Videos: Unifying Video Reasoning and Deep Research for Open-World Video Agents
- URL: http://arxiv.org/abs/2608.23329v2
- Date: Tue, 25 Aug 2026 13:58:46 GMT
- Title: Thinking Beyond Videos: Unifying Video Reasoning and Deep Research for Open-World Video Agents
- Abstract summary: We introduce VideoRover, a unified Video Deep Research framework that coordinates video cropping, multimodal search, and webpage browsing.<n>Given a video-question pair, VideoRover uses each tool result to select the next action, so localized video clips guide external retrieval and retrieved evidence triggers further video inspection and verification.<n>To develop this capability, we construct an automated data curation pipeline, producing 26K verified SFT trajectories and 3K challenging RL instances.
- Score: 50.87605650923757
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Open-world video understanding often requires a model to locate sparse visual evidence and acquire external knowledge that is absent from the video and its parametric memory. While Thinking-with-Videos enables active temporal perception and Deep Research supports multi-step information seeking, the two capabilities are typically developed in isolation. We introduce VideoRover, a unified Video Deep Research framework that iteratively coordinates video cropping, multimodal search, and webpage browsing. Given a video-question pair, VideoRover uses each tool result to select the next action, so localized video clips guide external retrieval and retrieved evidence triggers further video inspection and verification. To develop this capability, we construct an automated data curation pipeline, producing 26K verified SFT trajectories and 3K challenging RL instances. We also introduce VideoRover-Bench, a benchmark stratified by video duration and research difficulty. Experiments on VideoDR and VideoRover-Bench show that our VideoRover-8B-RL achieves performance comparable to proprietary models in the direct-answer setting without tool use while outperforming larger open-source models equipped with the same tool suite. Ablation studies and training dynamics further validate the complementary roles of active video grounding, external retrieval, and long-horizon reinforcement learning.
Related papers
- AdaVDR: Adaptive Tool Use and Reflection for Video Deep Research [34.906834225717795]
Video deep research answers complex questions by jointly understanding video content and retrieving external knowledge from the open Web.<n>We propose AdaVDR, an adaptive video deep research agent with adaptive tool invocation and reflection.<n>AdaVDR selects tools according to the task and its capabilities, and backtracks only when unreliable intermediate results require correction.
arXiv Detail & Related papers (2026-08-26T09:07:51Z) - VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning [55.2367119060441]
Video understanding is moving beyond closed-context perception toward open-world evidence exploration.<n>Existing multimodal search agents primarily target static images, and the current VDR benchmark relies on text-centric retrieval.<n>We propose VideoSearcher, a closed-loop agentic framework that empowers Vision-Language Models with multi-tool reasoning for VDR.
arXiv Detail & Related papers (2026-07-03T03:50:09Z) - Watching, Reasoning, and Searching: A Video Deep Research Benchmark on Open Web for Agentic Video Reasoning [32.71093573332936]
VideoDR is the first video deep research benchmark for studying video agents in open-web settings.<n>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.
arXiv Detail & Related papers (2026-01-11T15:07:37Z) - Video-BrowseComp: Benchmarking Agentic Video Research on Open Web [64.53060049124961]
Video-BrowseComp is a benchmark comprising 210 questions tailored for open-web agentic video reasoning.<n>It enforces a mandatory dependency on temporal visual evidence, ensuring answers cannot be derived solely through text search.<n>As the first open-web video research benchmark, Video-BrowseComp advances the field beyond passive perception toward proactive video reasoning.
arXiv Detail & Related papers (2025-12-28T19:08:27Z) - ARC-Hunyuan-Video-7B: Structured Video Comprehension of Real-World Shorts [56.75723197779384]
ARC-Hunyuan-Video is a multimodal model that processes visual, audio, and textual signals end-to-end for structured comprehension.<n>Our model is capable of multi-granularity timestamped video captioning and summarization, open-ended video question answering, temporal video grounding, and video reasoning.
arXiv Detail & Related papers (2025-07-28T15:52:36Z) - Deep Video Discovery: Agentic Search with Tool Use for Long-form Video Understanding [60.88843818016968]
Long-form video understanding presents significant challenges due to temporal-spatial complexity and difficulty of question answering.<n>We propose the Deep Video Discovery (DVD) agent to leverage an agentic search strategy over segmented video clips.<n>Our DVD agent achieves state-of-the-art performance on the challenging LVBench dataset, reaching an accuracy of 74.2%.
arXiv Detail & Related papers (2025-05-23T16:37:36Z) - VideoMind: A Chain-of-LoRA Agent for Long Video Reasoning [33.37714717781103]
VideoMind is a novel video-language agent designed for temporal-grounded video understanding.<n>We identify essential capabilities for video temporal reasoning and develop a role-based agentic workflow.<n>We propose a novel Chain-of-LoRA strategy, enabling seamless role-switching via lightweight LoRA adaptors.
arXiv Detail & Related papers (2025-03-17T17:59:33Z) - Generative Ghost: Investigating Ranking Bias Hidden in AI-Generated Videos [106.5804660736763]
Video information retrieval remains a fundamental approach for accessing video content.<n>We build on the observation that retrieval models often favor AI-generated content in ad-hoc and image retrieval tasks.<n>We investigate whether similar biases emerge in the context of challenging video retrieval.
arXiv Detail & Related papers (2025-02-11T07:43:47Z) - VideoRAG: Retrieval-Augmented Generation over Video Corpus [57.68536380621672]
VideoRAG is a framework that dynamically retrieves videos based on their relevance with queries.<n>VideoRAG is powered by recent Large Video Language Models (LVLMs)<n>We experimentally validate the effectiveness of VideoRAG, showcasing that it is superior to relevant baselines.
arXiv Detail & Related papers (2025-01-10T11:17:15Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.