Recent advances in DeepResearch-style agents have demonstrated strong capabilities in autonomous information acquisition and synthesize from real-world web environments. However, existing approaches remain fundamentally limited to text modality. Extending autonomous information-seeking agents to multimodal settings introduces critical challenges: the specialization-generalization trade-off that emerges when training models for multimodal tool-use at scale, and the severe scarcity of training data capturing complex, multi-step multimodal search trajectories. To address these challenges, we propose M3Searcher, a modular multimodal information-seeking agent that explicitly decouples information acquisition from answer derivation. M3Searcher is optimized with a retrieval-oriented multi-objective reward that jointly encourages factual accuracy, reasoning soundness, and retrieval fidelity. In addition, we develop MMSearchVQA, a multimodal multi-hop dataset to support retrieval centric RL training. Experimental results demonstrate that M3Searcher outperforms existing approaches, exhibits strong transfer adaptability and effective reasoning in complex multimodal tasks.
@article{arxiv.2601.09278,
title = {M$^3$Searcher: Modular Multimodal Information Seeking Agency with Retrieval-Oriented Reasoning},
author = {Xiaohan Yu and Chao Feng and Lang Mei and Chong Chen},
journal= {arXiv preprint arXiv:2601.09278},
year = {2026}
}