Thinking Beyond Videos: Unifying Video Reasoning and Deep Research for Open-World Video Agents

arXiv:2608.23329 · cs.CV, cs.AI · Submitted 2026-08-24 · Read on arXiv

cs.CV, cs.AI

Submitted: 2026-08-24

Updated: 2026-08-25

Project page: https://liuwq-bit.github.io/VideoRover

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Grounding — 20× in this paper · explained in 3 episodes
• Verification — 12× in this paper · explained in 2 episodes
• AGN — 9× in this paper · explained in 1 episode
• Reinforcement Learning — 9× in this paper · explained in 4 episodes
• Ablation — 7× in this paper · explained in 1 episode
• Benchmark — 6× in this paper · explained in 2 episodes
• Ablation Studies — 3× in this paper · explained in 1 episode
• Adam — 3× in this paper · explained in 2 episodes
• Visual Grounding — 3× in this paper · explained in 2 episodes
• Accuracy — 2× in this paper · explained in 1 episode
• Fine-Tuning — 2× in this paper · explained in 5 episodes
• Group Sequence Policy Optimization — 2× in this paper
• Active Perception — 1× in this paper · explained in 2 episodes
• Adaptive Reasoning — 1× in this paper · explained in 2 episodes
• Agentic Search — 1× in this paper · explained in 1 episode
• Multi-hop Reasoning — 1× in this paper · explained in 3 episodes
• RAG — 1× in this paper · explained in 3 episodes
• Retrieval-Augmented Generation (RAG) — 1× in this paper · explained in 16 episodes
• Trace — 1× in this paper · explained in 2 episodes
• Unified Framework — 1× in this paper · explained in 5 episodes

Sources

• Qwen3-VL Technical Report
• OpenSearch-VL: An Open Recipe for Frontier Multimodal Search Agents
• Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
• Retrieval-Augmented Generation for Large Language Models: A Survey
• Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning
• HyperEyes: Dual-Grained Efficiency-Aware Reinforcement Learning for Parallel Multimodal Search Agents
• Video-Browser: Towards Agentic Open-web Video Browsing
• Watching, Reasoning, and Searching: A Video Deep Research Benchmark on Open Web for Agentic Video Reasoning
• Watch, Remember, Reason: Human-View Video Understanding with MLLMs
• WebGPT: Browser-assisted question-answering with human feedback
• LookWise: Knowing When and Where to Look for Fine-Grained Visual Reasoning in Multimodal Large Language Models
• Deep Research: A Systematic Survey
• OpenAI GPT-5 System Card
• OpenThinkIMG: Learning to Think with Images via Visual Tool Reinforcement Learning
• DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
• A Comprehensive Survey of Deep Research: Systems, Methodologies, and Applications
• MM-DeepResearch: A Simple and Effective Multimodal Agentic Search Baseline
• Long Context Transfer from Language to Vision
• DynFrame: Adaptive Reasoning-Driven Multimodal Framework with Dynamic Frame Augmentation for Complex Video Understanding
• Group Sequence Policy Optimization

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models