VISTA：一种测试时自改进的视频生成智能体
VISTA: A Test-Time Self-Improving Video Generation Agent
把视频生成的质量提升从改模型转到改提示词：用多智能体在测试时迭代重写提示词，并用成对锦标赛选出最优样本，这套「生成—评估—反思—重写」的闭环可直接套用到任何黑盒视频或图像生成器上做免训练增强。
原文依据 a novel multi-agent system that autonomously improves video generation through refining prompts in an iterative loop
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论尽管文本到视频合成取得了快速进展，生成视频的质量仍然严重依赖于精确的用户提示词。在其他领域取得成功的现有测试时优化方法，难以应对视频的多面性。在本工作中，我们提出 VISTA（视频迭代自改进智能体），这是一种新颖的多智能体系统，通过迭代循环中的提示词精炼来自主提升视频生成质量。VISTA 首先将用户的想法分解为结构化的时序规划。生成之后，通过稳健的成对锦标赛选出最佳视频。随后，由分别关注视觉、音频与上下文保真度的三个专门智能体对这段获胜视频进行评判。最后，一个推理智能体综合这些反馈，以内省的方式重写并增强提示词，用于下一轮生成。在单场景与多场景视频生成场景上的实验表明，先前方法带来的收益并不稳定，而 VISTA 能持续提升视频质量以及与用户意图的对齐程度，相对于最优基线取得最高 60% 的成对胜率。人类评估者亦持相同看法，在 66.4% 的对比中更偏好 VISTA 的输出。
英文原文摘要 1197 字符
Despite rapid advances in text-to-video synthesis, generated video quality remains critically dependent on precise user prompts. Existing test-time optimization methods, successful in other domains, struggle with the multi-faceted nature of video. In this work, we introduce VISTA (Video Iterative Self-improvemenT Agent), a novel multi-agent system that autonomously improves video generation through refining prompts in an iterative loop. VISTA first decomposes a user's idea into a structured temporal plan. After generation, the best video is identified through a robust pairwise tournament. This winning video is then critiqued by a trio of specialized agents focusing on visual, audio, and contextual fidelity. Finally, a reasoning agent synthesizes this feedback to introspectively rewrite and enhance the prompt for the next generation cycle. Experiments on single- and multi-scene video generation scenarios show that while prior methods yield inconsistent gains, VISTA consistently improves video quality and alignment with user intent, achieving up to 60% pairwise win rate against state-of-the-art baselines. Human evaluators concur, preferring VISTA's outputs in 66.4% of comparisons.