# LogosKG: Hardware-Optimized Scalable and Interpretable Knowledge Graph Retrieval

arXiv: https://arxiv.org/abs/2604.18913 · HTML: https://mlsanity.com/paper/2604.18913/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning.
- Builds on 23 of its 45 references that are in the map.
- First posted on arXiv 20 Apr 2026.

## Placed in

- LLM reasoning / [Knowledge- and tool-augmented reasoning](https://mlsanity.com/lr/knowledge-and-tool-augmented-reasoning/)

## Builds on (most cited first, 23 of 23)

- [Fast Graph Representation Learning with PyTorch Geometric](https://mlsanity.com/paper/1903.02428/) (2019)
- [DDXPlus: A New Dataset For Automatic Medical Diagnosis](https://mlsanity.com/paper/2205.09148/) (2022)
- [GraphCare: Enhancing Healthcare Predictions with Personalized Knowledge Graphs](https://mlsanity.com/paper/2305.12788/) (2023)
- [FactKG: Fact Verification via Reasoning on Knowledge Graphs](https://mlsanity.com/paper/2305.06590/) (2023)
- [Knowledge Graph Retrieval-Augmented Generation for LLM-based Recommendation](https://mlsanity.com/paper/2501.02226/) (2025)
- [SNAP: A General Purpose Network Analysis and Graph Mining Library](https://mlsanity.com/paper/1606.07550/) (2016)
- [Building a PubMed knowledge graph](https://mlsanity.com/paper/2005.04308/) (2020)
- [Scalable Neural Methods for Reasoning With a Symbolic Knowledge Base](https://mlsanity.com/paper/2002.06115/) (2020)
- [Leveraging Medical Knowledge Graphs Into Large Language Models for Diagnosis Prediction: Design and Application Study](https://mlsanity.com/paper/2308.14321/) (2023)
- [KG4Diagnosis: A Hierarchical Multi-Agent LLM Framework with Knowledge Graph Enhancement for Medical Diagnosis](https://mlsanity.com/paper/2412.16833/) (2024)
- [Benchmark and Best Practices for Biomedical Knowledge Graph Embeddings](https://mlsanity.com/paper/2006.13774/) (2020)
- [Reasoning of Large Language Models over Knowledge Graphs with Super-Relations](https://mlsanity.com/paper/2503.22166/) (2025)
- [medIKAL: Integrating Knowledge Graphs as Assistants of LLMs for Enhanced Clinical Diagnosis on EMRs](https://mlsanity.com/paper/2406.14326/) (2024)
- [Mathematical Foundations of the GraphBLAS](https://mlsanity.com/paper/1606.05790/) (2016)
- [KERAP: A Knowledge-Enhanced Reasoning Approach for Accurate Zero-shot Diagnosis Prediction Using Multi-agent LLMs](https://mlsanity.com/paper/2507.02773/) (2025)
- [Overview of the Problem List Summarization (ProbSum) 2023 Shared Task on Summarizing Patients' Active Diagnoses and Problems from Electronic Health Record Progress Notes](https://mlsanity.com/paper/2306.05270/) (2023)
- [ClaimVer: Explainable Claim-Level Verification and Evidence Attribution of Text Through Knowledge Graphs](https://mlsanity.com/paper/2403.09724/) (2024)
- [AGENTiGraph: A Multi-Agent Knowledge Graph Framework for Interactive, Domain-Specific LLM Chatbots](https://mlsanity.com/paper/2508.02999/) (2025)
- [PubMed knowledge graph 2.0: Connecting papers, patents, and clinical trials in biomedical science](https://mlsanity.com/paper/2410.07969/) (2024)
- [TigerGraph: A Native MPP Graph Database](https://mlsanity.com/paper/1901.08248/) (2019)
- [Verify-in-the-Graph: Entity Disambiguation Enhancement for Complex Claim Verification with Interactive Graph Representation](https://mlsanity.com/paper/2505.22993/) (2025)
- [A Graph-based Verification Framework for Fact-Checking](https://mlsanity.com/paper/2503.07282/) (2025)
- [Brittleness and Promise: Knowledge Graph Based Reward Modeling for Diagnostic Reasoning](https://mlsanity.com/paper/2509.18316/) (2025)

## Abstract (arXiv)

Knowledge graphs (KGs) are increasingly integrated with large language models (LLMs) to provide structured, verifiable reasoning. A core operation in this integration is multi-hop retrieval, yet existing systems struggle to balance efficiency, scalability, and interpretability. We introduce LogosKG, a novel, hardware-aligned framework that enables scalable and interpretable k-hop retrieval on large KGs by building on symbolic KG formulations and executing traversal as hardware-efficient operations over decomposed subject, object, and relation representations. To scale to billion-edge graphs, LogosKG integrates degree-aware partitioning, cross-graph routing, and on-demand caching. Experiments show substantial efficiency gains over CPU and GPU baselines without loss of retrieval fidelity. With proven performance in KG retrieval, a downstream two-round KG-LLM interaction demonstrates how LogosKG enables large-scale, evidence-grounded analysis of how KG topology, such as hop distribution and connectivity, shapes the alignment between structured biomedical knowledge and LLM diagnostic reasoning, thereby opening the door for next-generation KG-LLM integration. The source code is publicly available at https://github.com/LARK-NLP-Lab/LogosKG, and an online demo is available at https://lark-nlp-lab-logoskg.hf.space/.