Retrieving evidence for language model queries from knowledge graphs requires balancing broad search across the graph with multi-hop traversal to follow relational links. Similarity-based retrievers provide coverage but remain shallow, whereas traversal-based methods rely on selecting seed nodes to start exploration, which can fail when queries span multiple entities and relations. We introduce ARK: Adaptive Retriever of Knowledge, an agentic KG retriever that gives a language model control over this breadth-depth tradeoff using a two-operation toolset: global lexical search over node descriptors and one-hop neighborhood exploration that composes into multi-hop traversal. ARK alternates between breadth-oriented discovery and depth-oriented expansion without depending on a fragile seed selection, a pre-set hop depth, or requiring retrieval training. ARK adapts tool use to queries, using global search for language-heavy queries and neighborhood exploration for relation-heavy queries. On STaRK, ARK reaches 59.1% average Hit@1 and 67.4 average MRR, improving average Hit@1 by up to 31.4% and average MRR by up to 28.0% over retrieval-based and agentic training-free methods. Finally, we distill ARK's tool-use trajectories from a large teacher into an 8B model via label-free imitation, improving Hit@1 by +7.0, +26.6, and +13.5 absolute points over the base 8B model on AMAZON, MAG, and PRIME datasets, respectively, while retaining up to 98.5% of the teacher's Hit@1 rate.

翻译：从知识图谱中为语言模型查询检索证据，需要在广泛的图谱搜索与沿关系链接的多跳遍历之间取得平衡。基于相似性的检索器覆盖范围广但深度不足，而基于遍历的方法依赖于选择起始节点来开始探索，当查询涉及多个实体和关系时可能失效。我们提出了ARK：自适应知识检索器，这是一种智能化的知识图谱检索器，它通过一个包含两种操作的工具集赋予语言模型控制广度-深度权衡的能力：对节点描述符的全局词汇搜索，以及可组合成多跳遍历的单跳邻域探索。ARK在不依赖脆弱的起始节点选择、预设跳数深度或需要检索训练的情况下，交替进行面向广度的发现和面向深度的扩展。ARK根据查询自适应地使用工具：对语言密集型查询使用全局搜索，对关系密集型查询使用邻域探索。在STaRK基准上，ARK达到了59.1%的平均Hit@1和67.4的平均MRR，相比基于检索的方法和无需训练的智能化方法，平均Hit@1最高提升了31.4%，平均MRR最高提升了28.0%。最后，我们通过无标签模仿学习，将大型教师模型中ARK的工具使用轨迹蒸馏到一个80亿参数的模型中，在AMAZON、MAG和PRIME数据集上，相比基础80亿参数模型，Hit@1分别绝对提升了+7.0、+26.6和+13.5个百分点，同时保留了高达98.5%的教师模型Hit@1水平。