Progressive Online Video Understanding with Evidence-Aligned Timing and Transparent Decisions

arXiv:2604.18459v1 Announce Type: new Abstract: Visual agents operating in the wild must respond to queries precisely when sufficient evidence first appears in a video stream, a critical capability that is overlooked by conventional video LLMs evaluated in offline settings. The shift to an online, streaming paradigm introduces significant challenges: a lack of decision transparency, the difficulty of aligning response timing with visual evidence, and the need to maintain a global, causally consistent understanding under tight computational budgets. To address these issues, we propose a novel framework that decouples reasoning control from memory integration. We introduce extbf{model{}}, an instantiation of this framework with two core components. First, the Active Thinking Decision Maker (ATDM) is a transparent reasoning controller that externalizes its decision process using observable progress (oldsymbol{rho}) and confidence (oldsymbol{c}) metrics. This allows it to precisely time its response t_r to match the first-sufficient-evidence timestamp t^star while streaming its reasoning to the user. Second, the Hierarchical Progressive Semantic Integration (HPSI) module acts as an efficient memory system. It employs a set of learnable, multi-level aggregation tokens that are propagated across clips to build a rich, global cognitive state without exceeding token budgets. %Our approach sets a new standard on key online video understanding benchmarks, achieving strong performance of extbf{71.6%} on StreamingBench and extbf{46.9%} on OVOBench, demonstrating a robust solution for evidence-aligned and transparent online video analysis. Extensive experiments demonstrate the effectiveness of ATDM and HPSI, e.g., Thinking-QwenVL improves the accuracy of the previous state-of-the-art from 67.63% to 71.60% on the StreamingBench benchmark.

Source: arXiv cs.CV | 2026-04-21

Related