用多智能体问答自动优化视频生成质量，无需模型内部信息。
VQQA: An Agentic Approach for Video Evaluation and Quality Improvement
- 通过生成视觉问题并用视觉语言模型给出语义反馈，实现闭环优化。
- 在文本到视频和图像到视频任务中分别提升11.57%和8.43%质量。
- 仅需少量迭代即可修复视觉瑕疵，适合快速改进生成结果的开发者。
尽管视频生成模型发展迅速，但其输出与复杂用户意图对齐仍具挑战。现有测试时优化方法通常计算成本高或需访问模型内部。为此，我们提出VQQA（视频质量问答），一种统一、多智能体框架，可泛化至多种输入模态和视频生成任务。通过动态生成视觉问题，并利用视觉语言模型（VLM）的批评作为语义梯度，VQQA将传统被动评估指标替换为可解释、可操作的反馈。这使得通过黑盒自然语言接口实现高效闭环提示优化成为可能。大量实验表明，VQQA能有效识别并消除视觉伪影，仅数次优化步骤即显著提升生成质量。该方法适用于文本到视频（T2V）和图像到视频（I2V）任务，在T2V-CompBench上绝对提升+11.57%，在VBench2上提升+8.43%，显著优于最先进的随机搜索与提示优化技术。
原文摘要 · Abstract (English)
Despite rapid advancements in video generation models, aligning their outputs with complex user intent remains challenging. Existing test-time optimization methods are typically either computationally expensive or require white-box access to model internals. To address this, we present VQQA (Video Quality Question Answering), a unified, multi-agent framework generalizable across diverse input modalities and video generation tasks. By dynamically generating visual questions and using the resulting Vision-Language Model (VLM) critiques as semantic gradients, VQQA replaces traditional, passive evaluation metrics with human-interpretable, actionable feedback. This enables a highly efficient, closed-loop prompt optimization process via a black-box natural language interface. Extensive experiments demonstrate that VQQA effectively isolates and resolves visual artifacts, substantially improving generation quality in just a few refinement steps. Applicable to both text-to-video (T2V) and image-to-video (I2V) tasks, our method achieves absolute improvements of +11.57% on T2V-CompBench and +8.43% on VBench2 over vanilla generation, significantly outperforming state-of-the-art stochastic search and prompt optimization techniques.
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。