Video-in-the-Loop: Span-Grounded Long Video QA with Interleaved Reasoning

We present Video-in-the-Loop (ViTL), a two-stage long-video QA framework that preserves a fixed token budget by first localizing question-relevant interval(s) with a low-fps skim and then answering via span-aware reallocation of visual tokens at higher effective frame rate, emitting an interleaved output with both spans and the final option for direct attribution. We also introduce dataname, which converts description based event graphs into span-grounded multiple-choice QA by pairing each question with ground-truth time span(s) and related reasoning. ViTL is trained end-to-end with an interleaved group-relative objective that couples temporal IoU for localization with answer correctness, allowing credit to flow from answers back to spans without increasing compute. Under fixed token budgets, ViTL attains up to 8.6% with 50% less frame input on long-video QA and temporal grounding (e.g., Charades-STA, ActivityNet-Captions) and ablations show that span-aware token reallocation consistently surpasses uniform sampling. Together, dataname and ViTL provide an interpretable, compute-efficient recipe for scalable long-video QA.