The Year in AI Papers
The year/Qwen

Paper 2508.05748

WebWatcher: Breaking New Frontier of Vision-Language Deep Research Agent

Xinyu Geng, Peng Xia, Zhen Zhang, Xinyu Wang, Qiuchen Wang, Ruixue Ding, Chenxi Wang, Jialong Wu, Yida Zhao, Kuan Li, Yong Jiang, Pengjun Xie, et al.

Published
Aug 2025
Research lab
Qwen
Citations
101
GitHub
20K stars

01 In brief

Summary

WebWatcher is a multimodal deep research agent introduced by Alibaba's Tongyi Lab to address the limitations of text-centric web agents by integrating visual information and complex reasoning.

It uses high-quality synthetic multimodal trajectories for cold-start training, multiple tools (web search, image search, webpage visit, code interpreter, OCR), and reinforcement learning (GRPO) to enhance generalization.

The authors also propose BrowseComp-VL, a challenging benchmark with 399 VQA pairs across two difficulty levels, requiring cross-modal inference and multi-step planning.

Experiments show WebWatcher-32B outperforms proprietary baselines (GPT-4o, Gemini-2.5-flash, Claude-3.7) and open-source agents on HLE, LiveVQA, MMSearch, and BrowseComp-VL, achieving 13.6% on HLE, 27.0% on BC-VL, 58.7% on LiveVQA, and 55.3% on MMSearch.

The paper details data generation pipelines, trajectory filtering, and training procedures, highlighting the importance of SFT cold start for RL stability and the agent's adaptive tool usage across benchmarks.

WebWatcher establishes a foundation for future multimodal deep research agents capable of solving real-world problems with autonomy and deep reasoning.

02 From the paper

Abstract

Web agents such as Deep Research have demonstrated superhuman cognitive abilities, capable of solving highly challenging information-seeking problems. However, most research remains primarily text-centric, overlooking visual information in the real world. This makes multimodal Deep Research highly challenging, as such agents require much stronger reasoning abilities in perception, logic, knowledge, and the use of more sophisticated tools compared to text-based agents. To address this limitation, we introduce WebWatcher, a multi-modal Agent for Deep Research equipped with enhanced visual-language reasoning capabilities. It leverages high-quality synthetic multimodal trajectories for efficient cold start training, utilizes various tools for deep reasoning, and further enhances generalization through reinforcement learning. To better evaluate the capabilities of multimodal agents, we propose BrowseComp-VL, a benchmark with BrowseComp-style that requires complex information retrieval involving both visual and textual information. Experimental results show that WebWatcher significantly outperforms proprietary baseline, RAG workflow and open-source agents in four challenging VQA benchmarks, which paves the way for solving complex multimodal information-seeking tasks.