DR-MMSearchAgent: Deepening Reasoning in Multimodal Search Agents

TL;DR

This paper introduces the Deepening Reasoning MMSearchAgent, a framework that enhances multimodal search agents by improving trajectory advantage signals and reducing redundancy, leading to state-of-the-art performance.

Contribution

It proposes a novel deep reasoning framework that leverages structural proximity and dynamic reward calibration for better multimodal agent performance.

Findings

Achieved 8.4% improvement over MMSearch-R1 on FVQA-test.

Constructed a multi-step reasoning dataset with 3602 high-quality QA pairs.

Demonstrated state-of-the-art results through extensive experiments.

Abstract

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.