先思考再验证，让模型更准地理解长视频。
Think, Then Verify: A Hypothesis-Verification Multi-Agent Framework for Long Video Understanding
- 先将答案转为可检验假设，再定位证据验证
- 在三个数据集上准确率领先，计算量更低
- 适合需要逻辑严谨性的长视频分析任务
长视频理解因视觉冗余密集、时序依赖长，且链式思维与检索类模型易累积语义漂移和相关性错误而困难。我们主张长视频推理应始于主动任务构建而非被动检索：模型须先明确每个候选答案成立所需的视频事实。这一“先思考后验证”原则催生了VideoHV-Agent框架，将视频问答重构为结构化假设验证流程。基于视频摘要，Thinker将答案候选转化为可检验假设，Judge提取区分性线索以确定需验证的证据，Verifier通过局部细粒度内容定位并测试线索，Answer代理整合验证结果输出最终答案。在三个长视频理解基准上的实验表明，VideoHV-Agent达到顶尖准确率，同时提升可解释性、逻辑严密性并降低计算开销。代码已开源：https://github.com/Haorane/VideoHV-Agent。
原文摘要 · Abstract (English)
Long video understanding is challenging due to dense visual redundancy, long-range temporal dependencies, and the tendency of chain-of-thought and retrieval-based agents to accumulate semantic drift and correlation-driven errors. We argue that long-video reasoning should begin not with reactive retrieval, but with deliberate task formulation: the model must first articulate what must be true in the video for each candidate answer to hold. This thinking-before-finding principle motivates VideoHV-Agent, a framework that reformulates video question answering as a structured hypothesis-verification process. Based on video summaries, a Thinker rewrites answer candidates into testable hypotheses, a Judge derives a discriminative clue specifying what evidence must be checked, a Verifier grounds and tests the clue using localized, fine-grained video content, and an Answer agent integrates validated evidence to produce the final answer. Experiments on three long-video understanding benchmarks show that VideoHV-Agent achieves state-of-the-art accuracy while providing enhanced interpretability, improved logical soundness, and lower computational cost. We make our code publicly available at: https://github.com/Haorane/VideoHV-Agent.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。