AI agents have seen widespread adoption in information retrieval for scientific research, giving rise to tools such as Deep Research. However, existing retrieval agents mainly rely on keyword- or embedding-based methods. While effective at capturing content-level similarities, they struggle to understand complex relational networks among scientific papers, such as identifying corroborating or conflicting studies and tracing technological lineages. This fundamental limitation often results in fragmented knowledge structures, misinterpreted research sentiment, and ineffective modeling of collective scientific progress. To address this limitation, we introduce SciNet, the first Scientific Network relation-aware dataset for information retrieval agents. Built on a meta-database of 269 million papers across 7 disciplines and containing 8,940 carefully designed tasks, SciNet systematically captures three levels of relational understanding: ego-centric retrieval of papers with novel knowledge structures, pairwise identification of scholarly relationships, and path-wise reconstruction of scientific evolution. Extensive evaluation of three categories of retrieval agents shows that their accuracy on relation-aware tasks often falls below 20%, highlighting a fundamental shortcoming of current retrieval paradigms. Importantly, in a downstream literature review application, agents empowered with SciNet achieve a 25.3% improvement in review quality, highlighting the critical value of relation-aware retrieval for deepening scientific insights. We publicly release SciNet at https://github.com/tsinghua-fib-lab/SciNet to support future research.

翻译：AI智能体在科学研究的信息检索领域已得到广泛应用，催生了诸如Deep Research等工具。然而，现有检索智能体主要依赖基于关键词或嵌入（embedding）的方法。尽管这些方法在捕捉内容级相似性方面表现有效，但它们在理解科学论文间复杂的关联网络时存在困难，例如识别相互证实或冲突的研究，以及追踪技术发展脉络。这一根本性限制常导致知识结构碎片化、研究情感解读错误，以及对集体科学进展建模的无效性。为应对此局限，我们提出了SciNet——首个面向信息检索智能体的科学网络关系感知数据集。SciNet基于涵盖7个学科、2.69亿篇论文的元数据库构建，包含8,940个精心设计的任务，系统性地捕捉三个层次的关系理解：以自我为中心检索具有新颖知识结构的论文、成对识别学术关系以及沿着路径重构科学演化过程。对三类检索智能体的广泛评估显示，它们在关系感知任务上的准确率通常低于20%，凸显了当前检索范式的根本缺陷。重要的是，在一项下游文献综述应用中，经SciNet赋能的智能体在综述质量上实现了25.3%的提升，突显了关系感知检索对于深化科学认知的关键价值。我们已在https://github.com/tsinghua-fib-lab/SciNet公开发布SciNet，以支持未来研究。