Struct-Searcher: Agentic Structural Thinking Advances Multimodal Deep Information Seeking
This work addresses the lack of principled conflict handling in multimodal information-seeking agents, offering a plug-and-play solution that improves accuracy across diverse models.
Struct-Searcher introduces a structural agentic workflow for multimodal deep information seeking that maintains an evolving graph to handle contradictory information, achieving a 17.2% average relative accuracy improvement on BrowseComp-VL across five backbones and outperforming state-of-the-art models by up to 3.7%.
Deep research agents have attracted increasing attention for their ability to collect large-scale online information to acquire target knowledge, with recent efforts shifting from purely text-based information seeking to multimodal settings. However, existing agentic workflows are largely aligned with evidence accumulation models, which linearly aggregate evidence and lack principled mechanisms for handling contradictory information across heterogeneous modalities. Towards this end, we propose Struct-Searcher, a structural agentic workflow grounded in belief revision theory that explicitly maintains an evolving multimodal structural graph throughout the reasoning process, enabling effective conflict-aware multimodal deep information seeking. Extensive experiments across multiple benchmark datasets and backbone models demonstrate that Struct-Searcher is (1) plug-and-play and model-agnostic, yielding an average relative accuracy improvement of 17.2% on BrowseComp-VL across five different backbones. (2) top-performing, consistently outperforming state-of-the-art vision-language models (VLMs) and deep research agents, with relative accuracy improvements of 3.7% on MM-BrowseComp, 1.5% on HLE-VL, and 0.7% on BrowseComp-VL over the second-best competing approach.