Deep research agents have emerged as powerful systems for addressing complex queries. Meanwhile, LLM-based retrievers have demonstrated strong capability in following instructions or reasoning. This raises a critical question: can LLM-based retrievers effectively contribute to deep research agent workflows? To investigate this, we introduce SAGE, a benchmark for scientific literature retrieval comprising 1,200 queries across four scientific domains, with a 200,000 paper retrieval corpus.We evaluate six deep research agents and find that all systems struggle with reasoning-intensive retrieval. Using DR Tulu as backbone, we further compare BM25 and LLM-based retrievers (i.e., ReasonIR and gte-Qwen2-7B-instruct) as alternative search tools. Surprisingly, BM25 significantly outperforms LLM-based retrievers by approximately 30%, as existing agents generate keyword-oriented sub-queries. To improve performance, we propose a corpus-level test-time scaling framework that uses LLMs to augment documents with metadata and keywords, making retrieval easier for off-the-shelf retrievers. This yields 8% and 2% gains on short-form and open-ended questions, respectively.

翻译：深度研究智能体已成为处理复杂查询的强大系统。与此同时，基于大语言模型的检索器在遵循指令和推理方面展现出卓越能力。这引出了一个关键问题：基于大语言模型的检索器能否有效支持深度研究智能体的工作流程？为探究此问题，我们提出了SAGE——一个面向科学文献检索的基准数据集，涵盖四个科学领域的1,200个查询，并包含20万篇论文的检索语料库。我们评估了六种深度研究智能体，发现所有系统在处理需要深度推理的检索任务时均存在困难。以DR Tulu为骨干框架，我们进一步比较了BM25与基于大语言模型的检索器（即ReasonIR和gte-Qwen2-7B-instruct）作为替代搜索工具的效果。令人惊讶的是，由于现有智能体生成的关键词导向子查询特性，BM25显著优于基于大语言模型的检索器约30%。为提升性能，我们提出了一种语料库级别的测试时扩展框架，利用大语言模型通过元数据和关键词增强文档表征，使现成检索器能更高效地执行检索。该框架在简答题和开放式问题上分别实现了8%和2%的性能提升。