VideoSearch-R1：通过软查询精炼的迭代视频检索与推理

摘要

随着视频语料库在规模和任务复杂性上持续增长，对能够从大规模语料库中检索相关视频（跨视频推理），并在检索到的内容中执行细粒度、查询条件驱动的任务（视频内推理，如时间定位）的方法需求日益增加。然而，现有方法通常将检索视为预处理步骤，因此当初始检索失败时，缺乏精细化搜索的机制，导致后续细粒度的视频内推理失效。此外，尽管近期基于智能体的框架在视频理解方面取得了进展，但这些框架通常假设与查询相关的视频已预先给定，仅专注于视频内推理任务。为应对这些局限，我们提出VideoSearch-R1——一个通过与视频搜索引擎进行多轮交互实现迭代式视频检索与推理的智能体框架。具体而言，我们引入软查询精细化（SQR），在连续潜在空间中精细化搜索查询令牌，而非在离散文本空间中重写查询，从而实现更高效、更细粒度的调整。SQR及其推理过程通过群组相对策略优化（GRPO）进行训练，并由从检索和下游任务中提取的任务级奖励信号引导。在此基础上，VideoSearch-R1在视频语料库时刻检索（VCMR）的三个数据集上取得了最先进的性能，能够从大规模语料库中迭代检索视频、精细化搜索查询，并在检索到的内容中执行精确的查询条件时间定位。分析表明，SQR能有效精细化原始查询，其所需生成的令牌数量显著少于明确的文本级查询精细化。代码和模型检查点已公开于mlvlab.github.io/VideoSearch-R1。

English

As video corpora continue to expand in both scale and task complexity, there is increasing demand for approaches that retrieve relevant videos from large-scale corpora (inter-video reasoning) and subsequently perform fine-grained, query-conditioned tasks (intra-video reasoning) within the retrieved content, such as temporal grounding. However, existing approaches typically treat retrieval as a preprocessing step, and consequently, when the initial retrieval fails, there is no mechanism to refine the search, leading to the failure of subsequent fine-grained intra-video reasoning. Moreover, while recent agentic frameworks have advanced video understanding, they typically assume that the query-relevant video is already given, focusing exclusively on intra-video reasoning tasks. To address these limitations, we propose VideoSearch-R1, an agentic framework for iterative video retrieval and reasoning through multi-turn interaction with a video search engine. Specifically, we introduce Soft Query Refinement (SQR) to refine search query tokens in a continuous latent space rather than rewriting queries in the discrete text space, enabling more efficient and fine-grained adjustments. SQR and its reasoning process are trained using Group Relative Policy Optimization (GRPO), guided by task-level reward signals derived from retrieval and downstream tasks. Building upon this, VideoSearch-R1 achieves state-of-the-art performance across three datasets on Video Corpus Moment Retrieval (VCMR), iteratively retrieving videos from large-scale corpora, refining search queries, and performing precise query-conditioned temporal grounding within the retrieved content. Our analyses show that SQR effectively refines the original query, requiring significantly fewer generated tokens than explicit text-level query refinement. Code and model checkpoints are publicly available at mlvlab.github.io/VideoSearch-R1.