Abstract
The rise of short-form video platforms and the emergence of multimodal large language models (MLLMs) have amplified the need for scalable, effective, zero-shot text-to-video retrieval systems. While recent advances in large-scale pretraining have improved zero-shot cross-modal alignment, existing methods still struggle with query-dependent temporal reasoning, limiting their effectiveness on complex queries involving temporal, logical, or causal relationships. To address these limitations, we propose an adaptive multi-agent retrieval framework that dynamically orchestrates specialized agents over multiple reasoning iterations based on the demands of each query. The framework includes: (1) a retrieval agent for scalable retrieval over large video corpora, (2) a reasoning agent for zero-shot contextual temporal reasoning, and (3) a query reformulation agent for refining ambiguous queries and recovering performance for those that degrade over iterations. These agents are dynamically coordinated by an orchestration agent, which leverages intermediate feedback and reasoning outcomes to guide execution. We also introduce a novel communication mechanism that incorporates retrieval-performance memory and historical reasoning traces to improve coordination and decision-making. Experiments on three TRECVid benchmarks spanning eight years show that our framework achieves a twofold improvement over CLIP4Clip and significantly outperforms state-of-the-art methods by a large margin.
Abstract (translated)
短视频平台的崛起以及多模态大型语言模型（MLLM）的出现，放大了对可扩展、有效零样本文本到视频检索系统的需求。尽管大规模预训练领域的近期进展改善了零样本跨模式对齐，现有的方法仍然在依赖查询的时间推理方面存在困难，这限制了它们处理涉及时间、逻辑或因果关系复杂查询的有效性。为了解决这些局限性，我们提出了一种自适应多代理检索框架，该框架根据每个查询的需求，在多个推理迭代中动态地协调专门的代理。此框架包括：（1）一个用于在大规模视频语料库上进行可扩展检索的检索代理；（2）一个执行零样本情境时间推理的理由代理；以及（3）一个通过细化模糊查询并恢复因迭代而性能下降的问题来提高性能的查询重构代理。这些代理由协调代理动态地协同工作，该协调代理利用中间反馈和推理结果来指导执行过程。我们还引入了一种新颖的通信机制，它结合了检索性能记忆和历史推理痕迹以改善协作和决策制定。在跨越八年的三个TRECVid基准测试上的实验表明，我们的框架在CLIP4Clip上实现了两倍以上的改进，并且显著地大幅超越了最先进的方法。
URL
https://arxiv.org/abs/2602.19040
