Long audio-video reasoning is difficult for omnimodal LLMs because the decisive evidence is often sparse, cross-modal, and too expensive to preserve with uniformly high-fidelity inputs. We introduce OmniReasoner, a tool-use post-training framework for Thinking with Long Audio-Video: omni-modal LLMs learn, via supervised fine-tuning and reinforcement learning, to decide whether and where to call a zoom-in tool before answering.
Video-IFBench is a new benchmark designed to evaluate how well multimodal large language models (MLLMs) follow user-specified instructions in video understanding tasks. It introduces an instruction taxonomy with four templates—single-task, multi-task, selection, and nested—covering 32 task types and 39 constraint categories that span semantic and format requirements. The benchmark was built using a semi-automatic pipeline that combines MLLMs, programmatic processing, and human verification, producing 1.5K samples, and a large-scale evaluation of over 20 recent MLLMs shows that instruction following remains difficult, especially for complex constraints and conditional structures.
By Hongbo Liu, Peixian Chen, Sihan Liu, Peiyuan Zhang, Kai Zou, Dian Zheng, Xiaoxing Hu, Yuhao Dong, Mengdan Zhang, Yunhang Shen, Haoyu Cao, Wei Liu, Weibo Gu, Xing Sun, Shengjie Zhao
OmniVBench introduces a comprehensive benchmark and a large-scale dataset for omni reference-to-video (R2V) generation, addressing gaps in existing evaluations that focus only on limited reference types and holistic consistency. The benchmark expands evaluation across 7 task families and 18 fine-grained tasks, covering content, motion, style, structure, narrative, and multi-reference settings, and employs a factor‑grounded evaluation with 12,172 checklist items to assess preservation, disentanglement, and routing of reference factors. The accompanying Omni‑R2V Dataset provides 340K training samples derived from professional video footage, along with task‑specific pipelines for scalable data construction, enabling broader research and revealing performance gaps in current R2V models.
By Wenxue Li, Peiyan Guan, Haoyang Jiang, Junxian Cai, Hualuo Liu, Chunjie Zhang, Chong Guan, Songlian Li, Taiyi Wu, Yongjian Yu, Xiaotong Zhao, Alan Zhao, Eric Liu, Xi Chen, Yu Liu, Lei Zhu
EgoBench is an interactive egocentric multimodal benchmark designed to evaluate tool-using AI agents. It contains 1,590 video‑grounded tasks across five daily scenarios and a user‑agent‑tool environment that enforces joint visual perception, multi‑hop reasoning, and dynamic interaction. The benchmark includes a simulated user for realistic feedback and a deterministic validation framework, revealing that current video‑MLLM agents achieve only a 34.95% average Joint Success Rate, highlighting significant capability gaps.
By Yunqi Liu, Tong Niu, Zitong Wang, Zhenlong Dai, Yuqi Qing, Weiqiang Wang, Jian Liu
OVIBench introduces the first standardized benchmark for evaluating vision‑language models on Online Video Question Answering under Interruption, a realistic setting where users can interrupt the model during answer generation. The benchmark categorizes interruptions into Cancellation, False Trigger, and Correction, supports both open‑ended and multiple‑choice tasks, and provides an offline simulation protocol plus a multi‑dimensional metric suite. Experiments show that OVIBench can distinguish models’ interruption‑handling abilities, particularly in following correction requests, and that fine‑tuning on the newly created OVI‑Train dataset yields significant performance gains.
By Naiming Liu, Zhiheng Wu, Shuning Wang, Tie Zhang, Bowen Liu, Tong Wang
arXiv:2602. 22897v3 Announce Type: replace Abstract: Human intelligence naturally intertwines omni-modal perception -- spanning vision, audio, and language -- with complex reasoning and tool usage to interact with the world.
By Xiaoxi Li, Wenxiang Jiao, Jiarui Jin, Haoxuan Li, Hao Wang, Shijian Wang, Guanting Dong, Jiajie Jin, Yinuo Wang, Yuan Lu, Ji-Rong Wen, Zhicheng Dou, Zhouchen Lin