Retrieval is being redefined by agentic AI, demanding multimodal reasoning beyond conventional similarity-based paradigms. Composed Image Retrieval (CIR) exemplifies this shift as each query combines a reference image with textual modifications, requiring compositional understanding across modalities. While embedding-based CIR methods have achieved progress, they remain narrow in perspective, capturing limited cross-modal cues and lacking semantic reasoning. To address these limitations, we introduce XR, a training-free multi-agent framework that reframes retrieval as a progressively coordinated reasoning process. It orchestrates three specialized types of agents: imagination agents synthesize target representations through cross-modal generation, similarity agents perform coarse filtering via hybrid matching, and question agents verify factual consistency through targeted reasoning for fine filtering. Through progressive multi-agent coordination, XR iteratively refines retrieval to meet both semantic and visual query constraints, achieving up to a 38% gain over strong training-free and training-based baselines on FashionIQ, CIRR, and CIRCO, while ablations show each agent is essential. Code is available: https://01yzzyu.github.io/xr.github.io/.

翻译：检索正被智能体人工智能重新定义，这要求超越传统基于相似性范式的多模态推理。组合图像检索（CIR）体现了这一转变，因为每个查询都结合了参考图像和文本修改，需要跨模态的组合理解。虽然基于嵌入的CIR方法已取得进展，但其视角仍然狭窄，捕获的跨模态线索有限且缺乏语义推理。为应对这些局限性，我们提出了XR——一个无需训练的多智能体框架，将检索重构为渐进协调的推理过程。它协调三种专门类型的智能体：想象智能体通过跨模态生成合成目标表示，相似性智能体通过混合匹配执行粗过滤，而提问智能体通过针对性推理验证事实一致性以实现细过滤。通过渐进式多智能体协调，XR迭代优化检索以满足语义和视觉查询约束，在FashionIQ、CIRR和CIRCO数据集上相比强大的无需训练和基于训练的基线方法实现了高达38%的性能提升，消融实验表明每个智能体都不可或缺。代码已公开：https://01yzzyu.github.io/xr.github.io/。