Technical Report

VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning

Zhenkun Gao^*1,2, Yicheng Bao^*1, Jinlong Peng^*†✉2, Xueheng Li^*✉3, Suyuan Huang^*4,2

Bangwei Liu¹, Kunquan Li⁵, Zhenye Gan², Tao Hu³, Chengjun Xie³, Xuanhua He^✉6

Zhizhong Zhang¹, Xin Tan¹, Chengjie Wang², Yuan Xie^✉1

^* Equal Contribution, ^† Project Lead, ✉ Corresponding Author

¹East China Normal University, ²Tencent Youtu Lab, ³University of Science and Technology of China, ⁴Wuhan University, ⁵Xiamen University, ⁶The Hong Kong University of Science and Technology

Paper BibTeX Code Coming Soon Dataset Coming Soon

VideoSearcher studies Video Deep Research, where an agent must localize visual evidence in videos, invoke external search tools, and synthesize answers through a single coherent reasoning trajectory.

Abstract

Video understanding is moving beyond closed-context perception toward open-world evidence exploration, a paradigm formalized as Video Deep Research (VDR). Existing multimodal search agents primarily target static images, and current VDR benchmarks rely on text-centric retrieval that discards crucial visual information. We propose VideoSearcher, a closed-loop agentic framework that empowers Vision-Language Models with multi-tool reasoning for VDR. VideoSearcher unifies temporal localization, spatial focusing, and multimodal search within a single reasoning trajectory, enabling agents to progressively ground visual clues, retrieve relevant evidence, and synthesize answers.

To optimize knowledge-intensive reasoning trajectories, we introduce Bi-branch Sequence Policy Optimization (BiSPO), which decouples tool-invocation optimization from answer-accuracy optimization. We further construct VideoSearch-QA, a benchmark for open-world video information grounding and multimodal search-based reasoning. Experiments show that VideoSearcher substantially improves over prior open-source agentic baselines across search-oriented and multimodal understanding benchmarks.

Method

VideoSearcher training and reasoning pipeline — VideoSearcher combines video grounding, spatial inspection, image search, and web search in a closed-loop reasoning process.

Video Grounding

The agent narrows long videos to relevant segments and locks key frames before searching for external evidence.

Multi-Tool Search

Image search and web search connect localized visual clues with open-world knowledge.

BiSPO Training

Answer correctness and tool-use behavior are optimized through separated reward branches.

Experiment Results

Search-oriented benchmark results — Search-oriented benchmark comparison under direct-answer and agentic workflows.

General video understanding results — General video understanding benchmark results.

Tool invocation statistics — Tool usage patterns across video and image search-oriented benchmarks.

Case Study

Qualitative examples illustrate how VideoSearcher builds a trajectory from video localization to visual entity search, evidence retrieval, and final answer synthesis.

Successful case 1: identifying a humanoid robot through visual grounding and external search.

Successful case 2: tracing a robot traffic police deployment location.

Failed case — Failure case: noisy retrieval feedback propagates into the final answer.

Citation

@article{gao2026videosearcher,
  title   = {VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning},
  author  = {Gao, Zhenkun and Bao, Yicheng and Peng, Jinlong and Li, Xueheng and Huang, Suyuan and Liu, Bangwei and Li, Kunquan and Gan, Zhenye and Hu, Tao and Xie, Chengjun and He, Xuanhua and Zhang, Zhizhong and Tan, Xin and Wang, Chengjie and Xie, Yuan},
  journal = {Technical Report},
  year    = {2026}
}