Autonomous Knowledge Graph Exploration with Adaptive Breadth-Depth Retrieval
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 40 of its 99 references that are in the map. First posted on arXiv 20 Jan 2026.
Builds on
40 of 99 references.
References · 40
- 2022Training language models to follow instructions with human feedbackcited by 15,971
- 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
- 2015Distilling the Knowledge in a Neural Networkcited by 10,324
- 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
- 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
- 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
- 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
- 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,141
- 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,453
- 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,210
- 2016Ups and Downs: Modeling the Visual Evolution of Fashion Trends with One-Class Collaborative Filteringcited by 520
- 2021Flow Network based Generative Models for Non-Iterative Diverse Candidate Generationcited by 392
28 more
- 2023Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoningcited by 328
- 2017DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoningcited by 266
- 2023Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graphcited by 238
- 2024Generative Representational Instruction Tuningcited by 233
- 2019PullNet: Open Domain Question Answering with Iterative Retrieval on Knowledge Bases and Textcited by 184
- 2017Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learningcited by 161
- 2019Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answeringcited by 147
- 2023Investigating the Factual Knowledge Boundary of Large Language Models with Retrieval Augmentationcited by 147
- 2015Inferring Networks of Substitutable and Complementary Productscited by 92
- 2024AvaTaR: Optimizing LLM Agents for Tool Usage via Contrastive Reasoningcited by 72
- 2025Voting or Consensus? Decision-Making in Multi-Agent Debatecited by 59
- 2024STaRK: Benchmarking LLM Retrieval on Textual and Relational Knowledge Basescited by 55
- 2025Distilling LLM Agent into Small Models with Retrieval and Code Toolscited by 47
- 2024Instruction Tuning With Loss Over Instructionscited by 40
- 2024HybGRAG: Hybrid Retrieval-Augmented Generation on Textual and Relational Knowledge Basescited by 29
- 2024Instruction Fine-Tuning: Does Prompt Loss Matter?cited by 26
- 2024Knowledge-Aware Query Expansion with Large Language Models for Textual and Relational Retrievalcited by 26
- 2024Ground Every Sentence: Improving Retrieval-Augmented LLMs with Interleaved Reference-Claim Generationcited by 21
- 2024RetroLLM: Empowering Large Language Models to Retrieve Fine-grained Evidence within Generationcited by 20
- 2025Ontology-Guided Reverse Thinking Makes Large Language Models Stronger on Knowledge Graph Question Answeringcited by 15
- 2024Tree-of-Traversals: A Zero-Shot Reasoning Algorithm for Augmenting Black-box Language Models with Knowledge Graphscited by 11
- 2025Mixture of Structural-and-Textual Retrieval over Text-rich Graph Knowledge Basescited by 11
- 2025ExpandR: Teaching Dense Retrievers Beyond Queries with LLM Guidancecited by 10
- 2025ReMindRAG: Low-Cost LLM-Guided Knowledge Graph Traversal for Efficient RAGcited by 8
- 2025Can Knowledge-Graph-based Retrieval Augmented Generation Really Retrieve What You Need?cited by 8
- 2024Database-Augmented Query Representation for Information Retrievalcited by 5
- 2025Search-on-Graph: Iterative Informed Navigation for Large Language Model Reasoning on Knowledge Graphscited by 5
- 2025Cooperative Retrieval-Augmented Generation for Question Answering: Mutual Information Exchange and Ranking by Contrasting Layerscited by 2
Built on by
Citing papers per year: 2026: 3.
3 papers.