GUI-explorer: Autonomous Exploration and Mining of Transition-aware Knowledge for GUI Agent
Bin Xie, Rui Shao, Gongwei Chen, Kaiwen Zhou, Yinchuan Li, Jie Liu, Min Zhang, Liqiang Nie
Abstract
GUI automation faces critical challenges in dynamic environments. MLLMs suffer from two key issues: misinterpreting UI components and outdated knowledge. Traditional fine-tuning methods are costly for app-specific knowledge updates. We propose GUI-explorer, a training-free GUI agent that incorporates two fundamental mechanisms: (1) Autonomous Exploration of Function-aware Trajectory. To comprehensively cover all application functionalities, we design a Function-aware Task Goal Generator that automatically constructs exploration goals by analyzing GUI structural information (e.g., screenshots and activity hierarchies). This enables systematic exploration to collect diverse trajectories. (2) Unsupervised Mining of Transition-aware Knowledge. To establish precise screen-operation logic, we develop a Transition-aware Knowledge Extractor that extracts effective screen-operation logic through unsupervised analysis the state transition of structured interaction triples (observation, action, outcome). This eliminates the need for human involvement in knowledge extraction. With a task success rate of 53.7% on SPA-Bench and 47.4% on AndroidWorld, GUI-explorer shows significant improvements over SOTA agents. It requires no parameter updates for new apps. GUI-explorer is open-sourced and publicly available at https://github.com/JiuTian-VL/GUI-explorer.
BibTeX
@inproceedings{xie-etal-2025-gui,
title = "{GUI}-explorer: Autonomous Exploration and Mining of Transition-aware Knowledge for {GUI} Agent",
author = "Xie, Bin and
Shao, Rui and
Chen, Gongwei and
Zhou, Kaiwen and
Li, Yinchuan and
Liu, Jie and
Zhang, Min and
Nie, Liqiang",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-long.282/",
doi = "10.18653/v1/2025.acl-long.282",
pages = "5650--5667",
ISBN = "979-8-89176-251-0"
}