Despite recent progress, Graphic User Interface (GUI) agents powered by Large Language Models (LLMs) struggle with complex mobile tasks due to limited app-specific knowledge. While UI Transition Graphs (UTGs) offer structured navigation representations, they are underutilized due to poor extraction and inefficient integration. We introduce KG-RAG, a Knowledge Graph-driven Retrieval-Augmented Generation framework that transforms fragmented UTGs into structured vector databases for efficient real-time retrieval. By leveraging an intent-guided LLM search method, KG-RAG generates actionable navigation paths, enhancing agent decision-making. Experiments across diverse mobile apps show that KG-RAG outperforms existing methods, achieving a 75.8% success rate (8.9% improvement over AutoDroid), 84.6% decision accuracy (8.1% improvement), and reducing average task steps from 4.5 to 4.1. Additionally, we present KG-Android-Bench and KG-Harmony-Bench, two benchmarks tailored to the Chinese mobile ecosystem for future research. Finally, KG-RAG transfers to web/desktop (+40% SR on Weibo-web; +20% on QQ Music-desktop), and a UTG cost ablation shows accuracy saturates at ~4h per complex app, enabling practical deployment trade-offs.
@article{arxiv.2509.00366,
title = {KG-RAG: Enhancing GUI Agent Decision-Making via Knowledge Graph-Driven Retrieval-Augmented Generation},
author = {Ziyi Guan and Jason Chun Lok Li and Zhijian Hou and Pingping Zhang and Donglai Xu and Yuzhi Zhao and Mengyang Wu and Jinpeng Chen and Thanh-Toan Nguyen and Pengfei Xian and Wenao Ma and Shengchao Qin and Graziano Chesi and Ngai Wong},
journal= {arXiv preprint arXiv:2509.00366},
year = {2025}
}