Jiahao Meng, Zhongyuan Bao, Yue Tan, Haiquan Wen, Renrui Zhang, Anna Wang, Jason Li, Yanwei Fu, Yunhai Tong, Ming-Hsuan Yang
备注：
Extension of Open-o3-Video (https://arxiv.org/abs/2510.20579). V2 extends single-pass grounded reasoning to agentic multi-turn evidence seeking and grounding, enabling models to actively acquire and reason over missing visual evidence. We further introduce STGR-v2-CoT-135K and CS-GRPO to improve evidence acquisition and grounded reasoning
Reliable video reasoning requires models to produce correct answers and expose supporting visual evidence. Open-o3-Video enables verifiable reasoning by embedding timestamps and object-level bounding boxes into reasoning traces, but is restricted to frames from an initial sparse sampler. We introduce Open-o3-Video-v2, which formulates video reasoning as a unified agentic evidencegrounded process. The model identifies missing information, acquires additional observations, grounds the moments and objects supporting its reasoning, and writes this evidence into the trajectory before continuing or answering. To support this behavior, we construct STGR-v2-CoT135K, including 52K multi-turn agentic grounded reasoning trajectories, and STGR-v2-RL-13K for reinforcement learning. We further propose Clue-Seek GRPO (CS-GRPO), which tracks how tool calls change accumulated evidence, rewards clue coverage and step-wise gains, and penalizes excessive, repetitive, or uninformative retrieval. On V-STaR, Open-o3-Video-v2-4B achieves 40.4% mAM and 56.3% mLGM, outperforming its Qwen3-VL-4B backbone by 8.5% and 12.6%, respectively. It also delivers consistent gains across general video understanding, long-video reasoning, and temporal grounding benchmarks. These results show that active evidence acquisition and verifiable object-level grounding are complementary for reliable video reasoning. The code and models are released at https://msalab-pku.github.io/projects/Open-o3-Video-v2.
Video-o3: Native Interleaved Clue Seeking for Long Video Multi-Hop Reasoning
Nanjing University（南京大学）；Shanghai AI Laboratory（上海人工智能实验室）；Shanghai Jiao Tong University（上海交通大学）；Peking University（北京大学）；University of Science and Technology of China（中国科学技术大学）；Zhejiang University（浙江大学）；SIAT, Chinese Academy of Sciences（中国科学院软件研究所）
Learning to Seek Evidence: A Verifiable Reasoning Agent with Causal Faithfulness Analysis
Institute of Biomedical Science, Fudan University（复旦大学生物医学研究院）；Fudan University（复旦大学）；Intelligent Medicine Institute, Fudan University（复旦大学智能医学研究院）；Shanghai Institute of Infectious Disease and Biosecurity, Fudan University（复旦大学传染病与生物安全研究所）；Shanghai Institute of Stem Cell Research and Clinical Translation, Fudan University（复旦大学干细胞研究与临床转化研究所）
Video-LMM Post-Training: A Deep Dive into Video Reasoning with Large Multimodal Models
University of Rochester（罗切斯特大学）；Northwestern University（西北大学）；CMU（卡内基梅隆大学）；UCSB（加州大学圣塔芭芭拉分校）；Purdue University（普渡大学）；UCLA（加州大学洛杉矶分校）；University of Oxford（牛津大学）；Brown University（布朗大学）；University of Virginia（弗吉尼亚大学）；Sony Group Corporation（索尼集团公司）
Video-Arena: A Scalable Agentic Video Benchmark for Spatiotemporal Capability
miHoYo Honkai AI R&D Team（米哈游崩坏AI研发团队）；College AI, Tsinghua University（清华大学人工智能学院）；University of Chinese Academy of Sciences（中国科学院大学）；MMLab, The University of Hong Kong（香港大学多媒体实验室）；National University of Singapore（新加坡国立大学）
DMTrack: Spatio-Temporal Multimodal Tracking via Dual-Adapter
Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences（中国科学院大学杭州高等研究院）；Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所）；Department of Computer Science and Engineering, University of North Texas（北卡罗来纳州立大学计算机科学与工程系）；OPPO AI Center（OPPO人工智能中心）
VBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoning
Nanyang Technological University（南洋理工大学）；University of California, Berkeley（加州大学伯克利分校）；University of California, San Diego（加州大学圣地亚哥分校）；The University of Tokyo（东京大学）；The Chinese University of Hong Kong（香港中文大学）；University of Michigan（密歇根大学）；Johns Hopkins University（约翰霍普金斯大学）；University of California, Davis（加州大学戴维斯分校）；University of California, Los Angeles（加州大学洛杉矶分校）；Carnegie Mellon University（卡内基梅隆大学）；Columbia University（哥伦比亚大学）；University of Toronto（多伦多大学）
EDVD-LLaMA: Explainable Deepfake Video Detection via Multimodal Large Language Model Reasoning
Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University（电子与电气工程系，香港理工大学）；School of Electrical and Electronic Engineering, Nanyang Technological University（电子与电气工程学院，南洋理工大学）；Shien-Ming Wu School of Intelligent Engineering, South China University of Technology（智能工程学院，华南理工大学）
Knowing Your Target: Target-Aware Transformer Makes Better Spatio-Temporal Video Grounding
University of Chinese Academy of Sciences（中国科学院大学）；Institute of Software Chinese Academy of Sciences（中国科学院软件研究所）；La Trobe University（拉筹伯大学）；University of North Texas（北得克萨斯大学）；Brookhaven National Laboratory（布鲁克海文国家实验室）
CLiViS: Unleashing Cognitive Map through Linguistic-Visual Synergy for Embodied Visual Reasoning
School of Computer Science and Technology, East China Normal University（东华大学计算机科学与技术学院）；King Abdullah University of Science and Technology（科廷大学）；Fudan University（复旦大学）
