DR-MMSearchAgent: Deepening Reasoning in Multimodal Search Agents

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Shengqin, Yan, Wentao, Zhou, Huichi, Chen, Yihang, Shao, Kun, Zhang, Zhizhong, Xie, Yuan
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915947274567680
author Wang, Shengqin
Yan, Wentao
Zhou, Huichi
Chen, Yihang
Shao, Kun
Zhang, Zhizhong
Xie, Yuan
author_facet Wang, Shengqin
Yan, Wentao
Zhou, Huichi
Chen, Yihang
Shao, Kun
Zhang, Zhizhong
Xie, Yuan
contents Agentic multimodal models have garnered significant attention for their ability to leverage external tools to tackle complex tasks. However, it is observed that such agents often meet premature interaction collapse, caused by two primary reasons: 1) the terminal reward often appending on the last token prevents the advantage from distinguishing trajectories with exploratory behavior; 2) excessively redundant context hinders the agent from absorbing useful feedback. To address these issues, we propose the Deepening Reasoning MMSearchAgent, the framework leverages the structural proximity to derive advantage signals from the whole rollout trajectories in an entire batch, such that trajectories of different lengths are further encouraged to be generated, even when containing the same correct answer. Additionally, differentiated gaussian rewards are employed to dynamically calibrate interaction tolerance, thereby ensuring information reliability and reduce redundancy. To support multi-turn interaction training, we have constructed a multi-step deep-reasoning dataset including 3602 high-quality QA pair with at least 3 reasonning steps. Extensive experiments demonstrate that our method achieves state-of-the-art performance, outperforming the MMSearch-R1 by 8.4$\%$ on FVQA-test.
format Preprint
id arxiv_https___arxiv_org_abs_2604_19264
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle DR-MMSearchAgent: Deepening Reasoning in Multimodal Search Agents
Wang, Shengqin
Yan, Wentao
Zhou, Huichi
Chen, Yihang
Shao, Kun
Zhang, Zhizhong
Xie, Yuan
Computer Vision and Pattern Recognition
Agentic multimodal models have garnered significant attention for their ability to leverage external tools to tackle complex tasks. However, it is observed that such agents often meet premature interaction collapse, caused by two primary reasons: 1) the terminal reward often appending on the last token prevents the advantage from distinguishing trajectories with exploratory behavior; 2) excessively redundant context hinders the agent from absorbing useful feedback. To address these issues, we propose the Deepening Reasoning MMSearchAgent, the framework leverages the structural proximity to derive advantage signals from the whole rollout trajectories in an entire batch, such that trajectories of different lengths are further encouraged to be generated, even when containing the same correct answer. Additionally, differentiated gaussian rewards are employed to dynamically calibrate interaction tolerance, thereby ensuring information reliability and reduce redundancy. To support multi-turn interaction training, we have constructed a multi-step deep-reasoning dataset including 3602 high-quality QA pair with at least 3 reasonning steps. Extensive experiments demonstrate that our method achieves state-of-the-art performance, outperforming the MMSearch-R1 by 8.4$\%$ on FVQA-test.
title DR-MMSearchAgent: Deepening Reasoning in Multimodal Search Agents
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.19264