cs.CVNov 12, 2026

FuGIBench: Evaluating Reliable Preparation in Streaming Video

Authors: Changheng Cai, Zhichao Huang, Song Ren, Zhichen Zhao, Hongsen Liu, Chaoyang Zheng, Wenxi Wu, Yuan Fang, 

Organizations: JD.com (jd.com) · The Hong Kong University of Science and Technology (ust.hk) · Tsinghua University (tsinghua.edu.cn)

Abstract

An assistant watching a worker can prepare for an emerging need before the worker is ready to receive help.As the need evolves, the assistant must maintain preparation until a response is due, or withdraw it if the need disappears. Video anticipation and interactive response benchmarks leave this interval between early evidence and response largely unmeasured. We introduce FuGIBench (Future-Grounded Interaction), a streaming-video benchmark in which a model chooses among waiting, reversible preparation, and response given a causal video prefix and a task contract. The benchmark contains 19,893 synthetic tool-assistance videos across ten tool tasks, in handover, ordinary-activity, and cancelled-need tracks. One primary score credits sustained preparation, incorporates response-interval alignment, and penalizes activity when the reference prescribes waiting. On a frozen set of 1,000 episodes, a reference system with a longer preparation lead has poorer response alignment, while similar handover leads accompany different levels of activity during ordinary work in matched scenarios. Together with cancellation analyses, these results show why evaluating preparation requires tracking decisions as needs develop, become actionable, or disappear.

Figures & tables

Explore similar work

CardsList
  1. LiveProBench: Can Streaming Video Models Really Interact Like Humans?

    Sep 11, 2026Kaixuan Du, Xin Wan, Hang Zhang +4Streaming Video UnderstandingVideo-Language Model Evaluation

  2. Don't Pause! Every prediction matters in a streaming video

    Apr 27, 2026Dibyadip Chatterjee, Zhanzhong Pang, Fadime Sener +2Streaming Video UnderstandingEfficient VLM Inference

  3. InteractionBench: A Real-Time Interaction Benchmark for Streaming Video Systems

    Oct 5, 2026Enxin Song, Suhao Yu, Yifei Xu +7Streaming Video UnderstandingVideo-Language Model Evaluation