Referring Video Object Segmentation (RVOS) aims to segment objects in videos based on textual queries. Current methods mainly rely on large-scale supervised fine-tuning (SFT) of Multi-modal Large Language Models (MLLMs). However, this paradigm suffers from heavy data dependence and limited scalability against the rapid evolution of MLLMs. Although recent zero-shot approaches offer a flexible alternative, their performance remains significantly behind SFT-based methods, due to the straightforward workflow designs. To address these limitations, we propose \textbf{Refer-Agent}, a collaborative multi-agent system with alternating reasoning-reflection mechanisms. This system decomposes RVOS into step-by-step reasoning process. During reasoning, we introduce a Coarse-to-Fine frame selection strategy to ensure the frame diversity and textual relevance, along with a Dynamic Focus Layout that adaptively adjusts the agent's visual focus. Furthermore, we propose a Chain-of-Reflection mechanism, which employs a Questioner-Responder pair to generate a self-reflection chain, enabling the system to verify intermediate results and generates feedback for next-round reasoning refinement. Extensive experiments on five challenging benchmarks demonstrate that Refer-Agent significantly outperforms state-of-the-art methods, including both SFT-based models and zero-shot approaches. Moreover, Refer-Agent is flexible and enables fast integration of new MLLMs without any additional fine-tuning costs. Code will be released at https://github.com/iSEE-Laboratory/Refer-Agent.

翻译：参考视频对象分割（RVOS）旨在根据文本查询分割视频中的对象。现有方法主要依赖于多模态大语言模型（MLLMs）的大规模监督微调（SFT）。然而，这种范式存在严重的数据依赖性，且面对MLLMs的快速演进时扩展性有限。尽管近期的零样本方法提供了一种灵活的替代方案，但由于其工作流程设计较为简单，其性能仍显著落后于基于SFT的方法。为应对这些局限，我们提出\textbf{Refer-Agent}，一种具有交替推理-反思机制的协作多智能体系统。该系统将RVOS分解为逐步推理过程。在推理阶段，我们引入一种从粗到精的帧选择策略，以确保帧的多样性与文本相关性，同时采用动态聚焦布局自适应地调整智能体的视觉焦点。此外，我们提出一种反思链机制，该机制利用提问者-应答者对生成自反思链，使系统能够验证中间结果并为下一轮推理优化生成反馈。在五个具有挑战性的基准测试上进行的大量实验表明，Refer-Agent显著优于最先进的方法，包括基于SFT的模型和零样本方法。此外，Refer-Agent具有灵活性，能够快速集成新的MLLMs而无需任何额外的微调成本。代码将在 https://github.com/iSEE-Laboratory/Refer-Agent 发布。