TransBench: Breaking Barriers for Transferable Graphical User Interface Agents in Dynamic Digital Environments

TL;DR

This paper introduces TransBench, a comprehensive benchmark for evaluating and improving the transferability of GUI agents across different platforms, versions, and applications, addressing key challenges in dynamic digital environments.

Contribution

We present TransBench, the first benchmark to systematically assess and enhance GUI agent transferability across multiple dimensions and diverse app categories.

Findings

Significant improvements in grounding accuracy with our methods.

TransBench effectively evaluates cross-version, cross-platform, and cross-application transferability.

Our code and data are publicly available for further research.

Abstract

Graphical User Interface (GUI) agents, which autonomously operate on digital interfaces through natural language instructions, hold transformative potential for accessibility, automation, and user experience. A critical aspect of their functionality is grounding - the ability to map linguistic intents to visual and structural interface elements. However, existing GUI agents often struggle to adapt to the dynamic and interconnected nature of real-world digital environments, where tasks frequently span multiple platforms and applications while also being impacted by version updates. To address this, we introduce TransBench, the first benchmark designed to systematically evaluate and enhance the transferability of GUI agents across three key dimensions: cross-version transferability (adapting to version updates), cross-platform transferability (generalizing across platforms like iOS, Android, and Web), and cross-application transferability (handling tasks spanning functionally distinct apps). TransBench includes 15 app categories with diverse functionalities, capturing essential pages across versions and platforms to enable robust evaluation. Our experiments demonstrate significant improvements in grounding accuracy, showcasing the practical utility of GUI agents in dynamic, real-world environments. Our code and data will be publicly available at GitHub.