VSearcher: Long-Horizon Multimodal Search Agent via Reinforcement Learning

• URL: http://arxiv.org/abs/2603.02795v1
• Date: Tue, 03 Mar 2026 09:33:22 GMT
• Title: VSearcher: Long-Horizon Multimodal Search Agent via Reinforcement Learning
• Authors: Ruiyang Zhang, Qianguo Sun, Chao Song, Yiyan Qi, Zhedong Zheng,
• Abstract summary: VSearcher is a multimodal search agent capable of long-horizon, multi-turn tool use in real-world web environments.<n>We introduce Iterative Injection Data Synthesis pipeline to generate large-scale, complex multimodal QA questions.<n>We then adopt an SFT-then-RL training pipeline to turn base multimodal models to agent capable of multi-turn tool calling in real-world web environments.
• Score: 22.27364585438247
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large models are increasingly becoming autonomous agents that interact with real-world environments and use external tools to augment their static capabilities. However, most recent progress has focused on text-only large language models, which are limited to a single modality and therefore have narrower application scenarios. On the other hand, multimodal large models, while offering stronger perceptual capabilities, remain limited to static knowledge and lack the ability to access and leverage up-to-date web information. In this paper, we propose VSearcher, turning static multimodal model into multimodal search agent capable of long-horizon, multi-turn tool use in real-world web environments, including text search, image search, and web browsing, via reinforcement learning. Specifically, we introduce Iterative Injection Data Synthesis pipeline to generate large-scale, complex multimodal QA questions, which are further filtered with comprehensive metrics to ensure high quality and sufficient difficulty. We then adopt an SFT-then-RL training pipeline to turn base multimodal models to agent capable of multi-turn tool calling in real-world web environments. Besides, we propose a multimodal search benchmark MM-SearchExam dedicated to evaluating search capabilities of multimodal search agents, which proves highly challenging for recent proprietary models. Extensive evaluations across multiple multimodal search benchmarks reveal effectiveness of our method. VSearcher achieves superior performance compared to recent multimodal search agents and even surpasses several proprietary models on multimodal web search tasks.

Related papers

• BrowseComp-$V^3$: A Visual, Vertical, and Verifiable Benchmark for Multimodal Browsing Agents [30.849897676091327]
  Multimodal large language models (MLLMs) are evolving into autonomous agents capable of performing multimodal web browsing and deep search in open-world environments.<n>We introduce BrowseComp-$V3$, a novel benchmark consisting of 300 carefully curated and challenging questions spanning diverse domains.<n>Our results highlight a fundamental gap between current model capabilities and robust multimodal deep search in real-world settings.
  arXiv  Detail & Related papers  (2026-02-13T12:25:13Z)
• Vision-DeepResearch: Incentivizing DeepResearch Capability in Multimodal Large Language Models [87.99592946216137]
  Vision-DeepResearch supports dozens of reasoning steps and hundreds of engine interactions.<n>Our Vision-DeepResearch supports dozens of reasoning steps and hundreds of engine interactions, resulting in a strong end-to-end multimodal deep-research MLLM.
  arXiv  Detail & Related papers  (2026-01-29T17:58:40Z)
• M$^3$Searcher: Modular Multimodal Information Seeking Agency with Retrieval-Oriented Reasoning [8.546005018618713]
  M$3$Searcher is a modular multimodal information-seeking agent.<n>M$3$Searcher is optimized with a retrieval-oriented multi-objective reward.<n> MMSearchVQA is a multimodal multi-hop dataset to support retrieval centric RL training.
  arXiv  Detail & Related papers  (2026-01-14T08:27:40Z)
• MUSE: A Simple Yet Effective Multimodal Search-Based Framework for Lifelong User Interest Modeling [48.18456242206804]
  We present a systematic analysis of how to leverage multimodal signals across both stages of lifelong modeling framework.<n>We propose MUSE, a simple yet effective multimodal search-based framework.<n>MUSE has been deployed in Taobao display advertising system, enabling 100K-length user behavior sequence modeling.
  arXiv  Detail & Related papers  (2025-12-08T06:55:13Z)
• DeepMMSearch-R1: Empowering Multimodal LLMs in Multimodal Web Search [61.77858432092777]
  We present DeepMMSearch-R1, the first multimodal large language model capable of performing on-demand, multi-turn web searches.<n>DeepMMSearch-R1 can initiate web searches based on relevant crops of the input image making the image search more effective.<n>We conduct extensive experiments across a range of knowledge-intensive benchmarks to demonstrate the superiority of our approach.
  arXiv  Detail & Related papers  (2025-10-14T17:59:58Z)
• WebWatcher: Breaking New Frontier of Vision-Language Deep Research Agent [68.3311163530321]
  Web agents such as Deep Research have demonstrated cognitive abilities, capable of solving highly challenging information-seeking problems.<n>This makes multimodal Deep Research highly challenging, as such agents require much stronger reasoning abilities in perception, logic, knowledge.<n>We introduce WebWatcher, a multi-modal Agent for Deep Research equipped with enhanced visual-language reasoning capabilities.
  arXiv  Detail & Related papers  (2025-08-07T18:03:50Z)
• MMSearch-R1: Incentivizing LMMs to Search [49.889749277236376]
  We present MMSearch-R1, the first end-to-end reinforcement learning framework that enables on-demand, multi-turn search in real-world Internet environments.<n>Our framework integrates both image and text search tools, allowing the model to reason about when and how to invoke them guided by an outcome-based reward with a search penalty.
  arXiv  Detail & Related papers  (2025-06-25T17:59:42Z)
• Generative Multimodal Models are In-Context Learners [60.50927925426832]
  We introduce Emu2, a generative multimodal model with 37 billion parameters, trained on large-scale multimodal sequences. Emu2 exhibits strong multimodal in-context learning abilities, even emerging to solve tasks that require on-the-fly reasoning.
  arXiv  Detail & Related papers  (2023-12-20T18:59:58Z)
• MultiBench: Multiscale Benchmarks for Multimodal Representation Learning [87.23266008930045]
  MultiBench is a systematic and unified benchmark spanning 15 datasets, 10 modalities, 20 prediction tasks, and 6 research areas. It provides an automated end-to-end machine learning pipeline that simplifies and standardizes data loading, experimental setup, and model evaluation. It introduces impactful challenges for future research, including robustness to large-scale multimodal datasets and robustness to realistic imperfections.
  arXiv  Detail & Related papers  (2021-07-15T17:54:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.