发表机构
Tsinghua University; Columbia University; Harbin Engineering University（清华大学; 哥伦比亚大学; 哈尔滨工程大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对视频时间定位中智能体框架手动优化困难的问题，提出VideoEvolve框架，通过完形填空式表示和分支引导演化自动改进框架，实验证明其有效提升多个基准上的定位性能。
AI 中文摘要
视频时间定位旨在根据自然语言查询在视频中定位事件。对于围绕冻结的视频-语言模型构建的智能体，其框架决定了查询如何引导时间预测以及这些预测如何被细化。手动细化这些框架需要诊断定位失败，并协调对智能体工作流程和指令的更改。我们提出了VideoEvolve，一个自动演化用于视频时间定位的智能体框架的框架。VideoEvolve采用完形填空式框架表示，保留阶段接口，同时使智能体工作流程和指令可被演化。分支引导的框架演化保留有前景的代码分支以供持续细化，利用执行反馈指导局部编辑，并通过验证确定哪些改进被保留。实验表明，在多个基准上定位性能得到提升。组件分析确定指令细化是一致收益的来源，而演化代码的收益因评估设置而异。这些结果共同支持自动框架演化作为改进视频时间定位的有效方法。代码可在该https网址获取。
英文摘要
Video temporal grounding aims to localize events in videos from natural-language queries. For agents built around frozen video-language models, the harness determines how queries guide temporal predictions and how those predictions are refined. Manually refining these harnesses requires diagnosing grounding failures and coordinating changes to both agent workflows and instructions. We introduce VideoEvolve, a framework that automatically evolves agent harnesses for video temporal grounding. VideoEvolve uses a Cloze-Structured Harness Representation that preserves stage interfaces while leaving agent workflows and instructions open to evolution. Branch-Guided Harness Evolution preserves promising code branches for continued refinement, using execution feedback to guide local edits and validation to determine which improvements are carried forward. Experiments demonstrate improved grounding performance across multiple benchmarks. Component analyses identify instruction refinement as a consistent source of gains, while the benefits of evolved code vary across evaluation settings. Together, these results support automated harness evolution as an effective approach to improving video temporal grounding. Code is available at https://github.com/bingjunluo/VideoEvolve .
