Toward a Human-Centered Evaluation Framework for Trustworthy LLM-Powered GUI Agents

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Chen, Chaoran, Zhang, Zhiping, Khalilov, Ibrahim, Guo, Bingcan, Gebreegziabher, Simret A, Ye, Yanfang, Xiao, Ziang, Yao, Yaxing, Li, Tianshi, Li, Toby Jia-Jun
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913876453359616
author Chen, Chaoran
Zhang, Zhiping
Khalilov, Ibrahim
Guo, Bingcan
Gebreegziabher, Simret A
Ye, Yanfang
Xiao, Ziang
Yao, Yaxing
Li, Tianshi
Li, Toby Jia-Jun
author_facet Chen, Chaoran
Zhang, Zhiping
Khalilov, Ibrahim
Guo, Bingcan
Gebreegziabher, Simret A
Ye, Yanfang
Xiao, Ziang
Yao, Yaxing
Li, Tianshi
Li, Toby Jia-Jun
contents The rise of Large Language Models (LLMs) has revolutionized Graphical User Interface (GUI) automation through LLM-powered GUI agents, yet their ability to process sensitive data with limited human oversight raises significant privacy and security risks. This position paper identifies three key risks of GUI agents and examines how they differ from traditional GUI automation and general autonomous agents. Despite these risks, existing evaluations focus primarily on performance, leaving privacy and security assessments largely unexplored. We review current evaluation metrics for both GUI and general LLM agents and outline five key challenges in integrating human evaluators for GUI agent assessments. To address these gaps, we advocate for a human-centered evaluation framework that incorporates risk assessments, enhances user awareness through in-context consent, and embeds privacy and security considerations into GUI agent design and evaluation.
format Preprint
id arxiv_https___arxiv_org_abs_2504_17934
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Toward a Human-Centered Evaluation Framework for Trustworthy LLM-Powered GUI Agents
Chen, Chaoran
Zhang, Zhiping
Khalilov, Ibrahim
Guo, Bingcan
Gebreegziabher, Simret A
Ye, Yanfang
Xiao, Ziang
Yao, Yaxing
Li, Tianshi
Li, Toby Jia-Jun
Human-Computer Interaction
Computation and Language
Cryptography and Security
The rise of Large Language Models (LLMs) has revolutionized Graphical User Interface (GUI) automation through LLM-powered GUI agents, yet their ability to process sensitive data with limited human oversight raises significant privacy and security risks. This position paper identifies three key risks of GUI agents and examines how they differ from traditional GUI automation and general autonomous agents. Despite these risks, existing evaluations focus primarily on performance, leaving privacy and security assessments largely unexplored. We review current evaluation metrics for both GUI and general LLM agents and outline five key challenges in integrating human evaluators for GUI agent assessments. To address these gaps, we advocate for a human-centered evaluation framework that incorporates risk assessments, enhances user awareness through in-context consent, and embeds privacy and security considerations into GUI agent design and evaluation.
title Toward a Human-Centered Evaluation Framework for Trustworthy LLM-Powered GUI Agents
topic Human-Computer Interaction
Computation and Language
Cryptography and Security
url https://arxiv.org/abs/2504.17934