@inproceedings{polonuer-etal-2026-autonomous,
    title = "Autonomous Knowledge Graph Exploration with Adaptive Breadth-Depth Retrieval",
    author = "Polonuer, Joaquin  and
      Vittor, Lucas  and
      Arango, I{\~n}aki  and
      Noori, Ayush  and
      Clifton, David A.  and
      Del Corro, Luciano  and
      Zitnik, Marinka",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.714/",
    pages = "15694--15709",
    ISBN = "979-8-89176-390-6",
    abstract = "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, a tool-using 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 agent-based 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."
}