OneSearch-VL: Unified Multimodal Deep Research Agent for Image and Video

arXiv:2610.12419 · cs.CV · Submitted 2026-10-08 · Read on arXiv

cs.CV

Submitted: 2026-10-08

Updated: 2026-10-08

Code: https://github.com/appletea233/OneSearch-VL

Terminology

• Benchmark — 43× in this paper · explained in 2 episodes
• Grounding — 31× in this paper · explained in 3 episodes
• Visual Grounding — 15× in this paper · explained in 2 episodes
• Reinforcement Learning — 13× in this paper · explained in 4 episodes
• Verifier — 10× in this paper · explained in 2 episodes
• GRPO — 7× in this paper · explained in 6 episodes
• Ablation — 6× in this paper · explained in 1 episode
• Aggregation — 5× in this paper · explained in 1 episode
• Fine-Tuning — 5× in this paper · explained in 5 episodes
• Graph Construction — 5× in this paper · explained in 3 episodes
• Core — 4× in this paper · explained in 2 episodes
• Provenance — 4× in this paper · explained in 3 episodes
• Trace — 4× in this paper · explained in 2 episodes
• Verification — 4× in this paper · explained in 2 episodes
• Accuracy — 3× in this paper · explained in 1 episode
• Actor — 3× in this paper · explained in 3 episodes
• Consistency — 3× in this paper · explained in 3 episodes
• Visually Grounded Evidence Graph — 3× in this paper
• Ablation Studies — 2× in this paper · explained in 1 episode
• Agentic Reasoning — 2× in this paper · explained in 1 episode
• Credit assignment — 2× in this paper · explained in 3 episodes
• Group Relative Policy Optimization — 2× in this paper
• Group Relative Policy Optimization (GRPO) — 2× in this paper · explained in 5 episodes
• Unified Framework — 2× in this paper · explained in 5 episodes
• Action Space — 1× in this paper · explained in 1 episode
• Agentic Search — 1× in this paper · explained in 1 episode
• Annotation Errors — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Calibration — 1× in this paper · explained in 7 episodes
• Council on Tall Buildings and Urban Habitat — 1× in this paper
• Embeddings — 1× in this paper · explained in 2 episodes
• GRPO Objective — 1× in this paper · explained in 2 episodes
• Hallucination — 1× in this paper · explained in 3 episodes
• Multi-hop Reasoning — 1× in this paper · explained in 3 episodes
• Multimodal Inputs — 1× in this paper · explained in 2 episodes
• Pipeline Parallel — 1× in this paper
• RAG — 1× in this paper · explained in 3 episodes
• Robustness — 1× in this paper · explained in 5 episodes

Sources

• Qwen3-VL Technical Report
• Seed2.0 Model Card: Towards Intelligence Frontier for Real-World Complexity
• OpenSearch-VL: An Open Recipe for Frontier Multimodal Search Agents
• Can Pre-trained Vision and Language Models Answer Visual Information-Seeking Questions?
• SenseNova-MARS: Empowering Multimodal Agentic Reasoning and Search via Reinforcement Learning
• Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
• Video-DeepResearch: Towards the Next-Generation Multimodal Deepresearch Agent
• Video-R1: Reinforcing Video Reasoning in MLLMs
• OneThinker: All-in-one Reasoning Model for Image and Video
• Seeking and Updating with Live Visual Knowledge
• VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning
• WebWatcher: Breaking New Frontier of Vision-Language Deep Research Agent
• DeepEyesV2: Toward Agentic Multimodal Model
• Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models
• Vision-DeepResearch: Incentivizing DeepResearch Capability in Multimodal Large Language Models
• SearchEyes: Towards Frontier Multimodal Deep Search Intelligence via Search World Simulation
• Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning
• Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking
• VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning
• Watching, Reasoning, and Searching: A Video Deep Research Benchmark on Open Web for Agentic Video Reasoning

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