AgentVidBench is a new multi‑hop video question‑answering benchmark designed to evaluate spatial, temporal, and causal reasoning in multimodal large language models (MLLMs). Unlike existing tests that focus on simple scene queries or global summaries, AgentVidBench includes step‑by‑step solution traces to assess whether agents gather the necessary evidence to justify their answers. Experiments with 12 MLLMs show limited single‑turn performance, but integrating these models into agentic workflows improves both accuracy and trajectory scores, establishing AgentVidBench as a comprehensive testbed for future research on agentic video understanding.
By Seoyeon An, Hyeonseo Jang, Minsu Kim, Chanho Lee, Younghan Park, Kangwook Lee
arXiv:2610.04432v2 Announce Type: replace
Abstract: Building interactive simulators from real-world observations is a promising way to scale embodied data, but current pipelines still rely heavily on...
By Jinzhou Tang, Zijun Zhang, Jing Yang, Yuchen Yan, Kun Zhou, Lingjun Mao, Ruobing Han, Jinglin Cao, Wenpeng Xu, Lukun He, Minghao Fu, Fan Feng, Biwei Huang
arXiv:2606. 26904v1 Announce Type: cross Abstract: Video reasoning language models implicitly assume that every input frame is equally reliable.
By Yangfan He, Yujin Choi, Jaehong Yoon
VibeVideoBench is a benchmark that evaluates multimodal agents capable of generating videos by writing code to render each frame and sound. The benchmark contains 239 self‑contained tasks in English and Chinese across 12 categories, requiring agents to produce a finished MP4 with sound within one hour without using any pre‑trained image or video generation model. Evaluation is hierarchical, using program checks, 13k task‑specific rubric checks, and five quality dimensions scored by three VLM judge panels, and it shows that GPT‑6 Astra and Claude Opus 5.5 perform best among nine frontier agents.
By Muxi Diao, Wenbin Xu, Lele Yang, Xuyang Ma, Yuzhe Chen, Jiankang Chen, Kaiyu Jiang, Changyi Liu, Haoyu Zhang, Hongyi Fu, Jianxiong Wang, Tianke Zhang, Haonan Fan, Yingxin Li, Bingyi Li, Xu Wang, Xuanyu Zheng, Bin Wen, Tingting Gao, Han Li, Wentao Zhang, Weiran Xu, Kongming Liang, Zhanyu Ma
arXiv:2609.37950v1 Announce Type: new
Abstract: Video understanding agents acquire evidence through an executable harness that controls what they observe and how they use those observations. However,...
By Bingjun Luo, Jialin Guo, Siqi Li
arXiv:2609.38413v1 Announce Type: new
Abstract: Vision-language models (VLMs) can answer questions about hour-long videos, but processing every frame is prohibitively expensive, even though the evide...
By Susan Liang, Jianmin Wu, Daxiang Dong
arXiv:2610.35864v1 Announce Type: new
Abstract: Diffusion video models produce striking clips, but they cannot reliably render an exact formula, a correct chart, a ruleconsistent game or narration sy...
By Muxi Diao, Wenbin Xu, Lele Yang, Xuyang Ma, Yuzhe Chen, Jiankang Chen, Kaiyu Jiang, Changyi Liu, Haoyu Zhang, Hongyi Fu, Jianxiong Wang, Tianke Zhang, Haonan Fan, Yingxin Li, Bingyi Li, Xu Wang, Xuanyu Zheng, Bin Wen, Tingting Gao, Han Li, Wentao Zhang, Weiran Xu, Kongming Liang, Zhanyu Ma
The paper introduces LARVA, a framework that distills multi‑round video agents by jointly learning latent reasoning and visual observations. Instead of using textual captions, an observer sends compact continuous representations to a reasoner, which then selects the next action or produces an answer. The approach incorporates action and answer supervision through this interface and uses observation reconstruction and reasoning‑distribution alignment as auxiliary signals, achieving strong results on five video‑understanding benchmarks with 4B and 7B models.
By Junzhang Liu, Hao Yuan, Qi Zhang, Yiming Wu, Long Chen, Zhecan Wang
arXiv:2512. 05774v2 Announce Type: replace-cross Abstract: Long video understanding (LVU) is challenging because answering real-world queries often depends on sparse, temporally dispersed cues buried in hours of mostly redundant and irrelevant content.
By Ziyang Wang, Honglu Zhou, Shijie Wang, Junnan Li, Caiming Xiong, Silvio Savarese, Mohit Bansal, Michael S. Ryoo, Juan Carlos Niebles
AgentVQA is an offline benchmark designed to evaluate vision‑language models on realistic agentic scenarios across five domains: Web Agents, Robotics, Egocentric Videos, Games, and Spatial Planning. It comprises 1,000 carefully selected real‑world examples drawn from 23 source datasets, enabling reliable comparisons without costly online simulations. The benchmark reveals that current models achieve only 58.5% accuracy, with most errors stemming from difficulties in grounding and tracking evolving visual states rather than from task misunderstanding or reasoning.
By Advait Gupta, Sachin Konan, Tom Yin, Gabriel Sarch, Zhuang Liu
arXiv:2608. 08612v1 Announce Type: cross Abstract: Recently, retrieval-augmented and memory-augmented methods have emerged as two promising paradigms for long-video question answering.
By Caijun Yan, Yang Zhou, Meixing Shi, Haoran Sun, Yichen Li, Yuxiang Cai, Yankai Jiang
arXiv:2607. 27380v2 Announce Type: replace-cross Abstract: Text-to-video models have achieved remarkable visual quality, yet they still struggle to generate physically consistent dynamics because the temporal evolution of a scene must be inferred implicitly from a highly compressed text prompt.
By Haodong Li, Tianfei Ren, Xiaoxiao Ma, Chunmei Qing, Zhen Fang, Sipeng He, Ziyu Guo, Haoyu Wu, Juanxi Tian, Yihang Zou, Ruichuan An, Dongzhi Jiang, Boxue Yang, Ji Xie, Xu Huang, Wenhao Yan, Jialv Zou, Zhengrong Yue, Yaxin Luo, Xiaotong Li, Yuzhu Wang, Junyan Ye, Jinjing Zhao, Zehui Chen, Lin Chen, Renye Yan, Feng Zhao, Pheng-Ann Heng