# KGCache: Amortized Subgraph Retrieval for KG Reasoning with LLMs

arXiv: https://arxiv.org/abs/2608.07954 · HTML: https://mlsanity.com/paper/2608.07954/

## 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 10 of its 21 references that are in the map.
- First posted on arXiv 8 Aug 2026.

## Placed in

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

## Builds on (most cited first, 10 of 10)

- [Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph](https://mlsanity.com/paper/2307.07697/) (2023)
- [Non-Determinism of "Deterministic" LLM Settings](https://mlsanity.com/paper/2408.04667/) (2024)
- [Simple Is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation](https://mlsanity.com/paper/2410.20724/) (2024)
- [Plan-on-Graph: Self-Correcting Adaptive Planning of Large Language Model on Knowledge Graphs](https://mlsanity.com/paper/2410.23875/) (2024)
- [Think-on-Graph 2.0: Deep and Faithful Large Language Model Reasoning with Knowledge-guided Retrieval Augmented Generation](https://mlsanity.com/paper/2407.10805/) (2024)
- [ReasoningLM: Enabling Structural Subgraph Reasoning in Pre-trained Language Models for Question Answering over Knowledge Graph](https://mlsanity.com/paper/2401.00158/) (2023)
- [Think-on-Graph 3.0: Efficient and Adaptive LLM Reasoning on Heterogeneous Graphs via Multi-Agent Dual-Evolving Context Retrieval](https://mlsanity.com/paper/2509.21710/) (2025)
- [KARPA: A Training-free Method of Adapting Knowledge Graph as References for Large Language Model's Reasoning Path Aggregation](https://mlsanity.com/paper/2412.20995/) (2024)
- [Search-on-Graph: Iterative Informed Navigation for Large Language Model Reasoning on Knowledge Graphs](https://mlsanity.com/paper/2510.08825/) (2025)
- [Query-Aware Graph Neural Networks for Enhanced Retrieval-Augmented Generation](https://mlsanity.com/paper/2508.05647/) (2025)

## Abstract (arXiv)

Large language models can answer knowledge-intensive questions more reliably when they are grounded with knowledge graphs, but systems such as Think-on-Graph and Reasoning-on-Graph repeatedly query the same graph neighborhoods across different questions. In this work, we study this repeated retrieval in Knowledge Graph Question Answering~(KGQA) workloads and propose KGCache, an in-memory cache for one-hop knowledge graph neighborhoods. KGCache is designed to be compatible with both iterative traversal (ToG) and one shot planning (RoG) KGQA paradigms. KGCache is placed between the KGQA engine and the backend serving the KG, so repeated entity requests can be served from cache instead of issuing new KG queries. We evaluate KGCache on WebQSP and CWQ using LRU, LFU, and a trace-aware Oracle policy. Our analysis shows that both datasets contain substantial entity reuse among starting entities and entities reached during traversal. We also explore semantic caching for similar queries, which shows additional hit-rate gains on WebQSP and needs further accuracy testing on CWQ. Entity caching accelerates KG retrieval by up to 1.91×, while semantic-context caching achieves up to 1.06× full-system speedup in the evaluated WebQSP configurations, with each hit being up to 3.73× faster.