Saved in:
Bibliographic Details
Main Authors: Yu, Xiaohan, Feng, Chao, Mei, Lang, Chen, Chong
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.09278
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908764058157056
author Yu, Xiaohan
Feng, Chao
Mei, Lang
Chen, Chong
author_facet Yu, Xiaohan
Feng, Chao
Mei, Lang
Chen, Chong
contents 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 M$^3$Searcher, a modular multimodal information-seeking agent that explicitly decouples information acquisition from answer derivation. M$^3$Searcher 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 M$^3$Searcher outperforms existing approaches, exhibits strong transfer adaptability and effective reasoning in complex multimodal tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2601_09278
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle M$^3$Searcher: Modular Multimodal Information Seeking Agency with Retrieval-Oriented Reasoning
Yu, Xiaohan
Feng, Chao
Mei, Lang
Chen, Chong
Artificial Intelligence
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 M$^3$Searcher, a modular multimodal information-seeking agent that explicitly decouples information acquisition from answer derivation. M$^3$Searcher 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 M$^3$Searcher outperforms existing approaches, exhibits strong transfer adaptability and effective reasoning in complex multimodal tasks.
title M$^3$Searcher: Modular Multimodal Information Seeking Agency with Retrieval-Oriented Reasoning
topic Artificial Intelligence
url https://arxiv.org/abs/2601.09278