GUI-explorer: Autonomous Exploration and Mining of Transition-aware Knowledge for GUI Agent

TL;DR

GUI-explorer is a training-free GUI agent that autonomously explores and mines transition-aware knowledge from GUIs, significantly improving app interaction success rates without requiring parameter updates.

Contribution

It introduces a novel, training-free approach combining autonomous exploration and unsupervised knowledge mining for GUI agents, eliminating the need for costly fine-tuning.

Findings

Achieves 53.7% success on SPA-Bench

Achieves 47.4% success on AndroidWorld

Outperforms state-of-the-art agents significantly

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 MLLMs suffer from two key issues: misinterpreting UI components and outdated knowledge.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.