SOURCE-LINKED INTELLIGENCE

Finding the Right Evidence: Factor-Guided Coarse-to-Fine Reasoning for Long Videos

arXiv · AI, language, vision and robotics · article · Aug 26, 2026 · UTC

While LVLMs rapidly improve, long-video question answering still remains challenging: relevant evidence is sparse, and question-relevant context often fails to provide cues that discriminate the correct answer from plausible alternatives. Diagnostic analysis on a manually annotated subset of MMR-V shows that prior agentic systems substantially improve cue retrieval over direct VLM inference yet fail to achieve a corresponding gain in answer accuracy, indicating that the bottleneck lies in option-discriminative evidence rather than topical relevance alone. We propose PACE (Progressive Acquisiti

Read original source ↗ Open in workspace

recordType

paper

region

Global