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.
AgentVista: Evaluating Multimodal Agents in Ultra-Challenging Realistic Visual Scenarios
Hong Kong University of Science and Technology(香港理工大学);Zhejiang University(浙江大学);National University of Singapore(新加坡国立大学);University of North Carolina at Chapel Hill(北卡罗来纳大学教堂山分校)
MMSearch-OPD: Easy Made Hard, Hard Made Learnable for Long-Horizon Multimodal Search Agents
Peking University(北京大学);HKUST(GZ)(香港科技大学(广州));Tsinghua University(清华大学);The University of Hong Kong(香港大学);Zhejiang University(浙江大学);Huawei Cloud BU(华为云业务部)
StreamArena: Toward Continuous, Interactive, and Long-Horizon Agentic Streaming Video Understanding
The Hong Kong University of Science and Technology(香港科技大学);Xiaohongshu Inc.(小红书公司);The University of Hong Kong(香港大学);The Chinese University of Hong Kong(香港中文大学)
Response-Aware Multimodal Learning for Post-Treatment Visual Acuity Forecasting
Research Convergence Institute(研究融合研究所);Sungkyunkwan University(全北大学);Dept. of AI Systems Engineering(人工智能系统工程系);Dept. of Ophthalmology(眼科系);Kyung Hee University Medical Center(庆熙大学医学院);Dept. of Electrical and Computer Engineering(电气与计算机工程系)
GEM: A Generalizable Ego-Vision Multimodal World Model for Fine-Grained Ego-Motion, Object Dynamics, and Scene Composition Control
École Polytechnique Fédérale de Lausanne (EPFL)(洛桑联邦理工学院(EPFL));University of Bern(伯尔尼大学);Swiss Data Science Center(瑞士数据科学中心);University of Zurich(苏黎世大学);ETH Zurich(苏黎世联邦理工学院)
MagicWorld: Towards Long-Horizon Stability for Interactive Video World Exploration
College of Computer Science and Technology, Zhejiang University(浙江大学计算机科学与技术学院);vivo BlueImage Lab, vivo Mobile Communication Co., Ltd.(vivo蓝影实验室,vivo移动通信有限公司);National University of Singapore(新加坡国立大学)
From Verbatim to Gist: Distilling Pyramidal Multimodal Memory via Semantic Information Bottleneck for Long-Horizon Video Agents
Tsinghua Shenzhen International Graduate School, Tsinghua University(清华大学深圳国际研究生院,清华大学);Harbin Institute of Technology, Shenzhen(哈尔滨工业大学深圳校区);Peng Cheng Laboratory(鹏城实验室)
Enhancing Vision-Language Navigation with Multimodal Event Knowledge from Real-World Indoor Tour Videos
The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));Tsinghua University(清华大学);Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI)(马尔代夫 bin Zayed 大学人工智能学院);Hangzhou City University(杭州城市学院)
LongSpace: Exploring Long-Horizon Spatial Memory from Perception to Recall in Video
Beijing University of Posts and Telecommunications(北京邮电大学);Zhongguancun Academy(中关村学院);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);The Chinese University of Hong Kong(香港中文大学);Xi’an Jiaotong University(西安交通大学)
Vision-as-Inverse-Graphics Agent via Interleaved Multimodal Reasoning
University of California, Berkeley(加州大学伯克利分校);Carnegie Mellon University(卡内基梅隆大学);Max Planck Institute for Intelligent Systems(马克斯·普朗克智能系统研究所);Impossible, Inc.(Impossible公司)