Deep Research agents are rapidly emerging as primary consumers of modern retrieval systems. Unlike human users who issue and refine queries without documenting their intermediate thought processes, Deep Research agents generate explicit natural language reasoning before each search call, revealing rich intent and contextual information that existing retrievers entirely ignore. To exploit this overlooked signal, we introduce: (1) Reasoning-Aware Retrieval, a retrieval paradigm that jointly embeds the agent's reasoning trace alongside its query; and (2) DR-Synth, a data synthesis method that generates Deep Research retriever training data from standard QA datasets. We demonstrate that both components are independently effective, and their combination yields a trained embedding model, AgentIR-4B, with substantial gains. On the challenging BrowseComp-Plus benchmark, AgentIR-4B achieves 68\% accuracy with the open-weight agent Tongyi-DeepResearch, compared to 50\% with conventional embedding models twice its size, and 37\% with BM25. Code and data are available at: https://texttron.github.io/AgentIR/.

翻译：深度研究智能体正迅速成为现代检索系统的主要使用者。与人类用户仅提交并优化查询而不记录其中间思考过程不同，深度研究智能体在每次搜索调用前会生成显式的自然语言推理，这些推理揭示了丰富的意图与上下文信息，而现有检索器完全忽略了这些信息。为利用这一被忽视的信号，我们提出：（1）推理感知检索——一种将智能体的推理轨迹与其查询联合编码的检索范式；（2）DR-Synth——一种从标准问答数据集生成深度研究检索器训练数据的数据合成方法。我们证明这两个组件各自独立有效，且它们的组合可训练出嵌入模型 AgentIR-4B，并带来显著性能提升。在具有挑战性的 BrowseComp-Plus 基准测试中，AgentIR-4B 与开源权重智能体 Tongyi-DeepResearch 配合实现了 68% 的准确率，而参数量为其两倍的传统嵌入模型仅达到 50%，BM25 方法则为 37%。代码与数据公开于：https://texttron.github.io/AgentIR/。