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

TL;DR

WebWatcher is a multimodal vision-language agent designed for deep research tasks, leveraging synthetic data, tool integration, and reinforcement learning to enhance reasoning and outperform existing models in complex visual-textual benchmarks.

Contribution

Introduction of WebWatcher, a novel multimodal agent with advanced visual-language reasoning, trained on synthetic data and reinforced for better generalization in complex tasks.

Findings

WebWatcher outperforms baseline models in four VQA benchmarks.

Synthetic multimodal trajectories improve training efficiency.

Reinforcement learning enhances WebWatcher's generalization capabilities.

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.