2025/08/07 by Xinyu Geng, Peng Xia, Geng, Xinyu +25 · 1 voice · 32 citations
Computer Science · #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Information Retrieval (cs.IR) #Multimodal Machine Learning Applications #Topic Modeling #cs.IR
paper · pdf · doi:10.48550/arxiv.2508.05748
openalex publication_date 2025/08/07 · arxiv published 2025/08/07 · arxiv updated 2025/09/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
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.