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

2026-08-26

AI Summary

为解决长视频问答中正确答案证据稀疏问题，提出PACE框架，通过因子引导的粗到细推理方法有效获取关键证据，提高回答准确性。

Abstract

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 Acquisition of Critical Evidence), a factor-guided framework for long-video evidence acquisition. PACE proceeds in two stages: it first indexes clip-level descriptions guided by question-derived factors without observing the candidate answers; it then uses the candidate answers to derive contrastive cues and queries the index for verification. On MMR-V with the open-source Qwen3-VL backbone, PACE achieves 42.6% accuracy, outperforming direct inference and prior agentic baselines including Deep Video Discovery (DVD). On the same diagnostic subset, PACE recovers 66.9% of the annotated cues, providing empirical evidence that its gains are associated with improved evidence recovery rather than stronger answer-side priors alone. Consistent gains over DVD on LVBench, Video-MME, EgoSchema, and LongVideoBench suggest that option-aware evidence acquisition transfers beyond MMR-V. Code is available at https://github.com/HKUST-KnowComp/PACE.

Problem

• long-video question answering
• sparse evidence
• contextual cues
• answer discrimination

Innovation

• PACE
• factor-guided framework
• long-video evidence acquisition
• contrastive cues
• option-discriminative evidence