Mobile-Env: Building Qualified Evaluation Benchmarks for LLM-GUI Interaction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Danyang, Shen, Zhennan, Xie, Rui, Zhang, Situo, Xie, Tianbao, Zhao, Zihan, Chen, Siyuan, Chen, Lu, Xu, Hongshen, Cao, Ruisheng, Yu, Kai
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917691892170752
author Zhang, Danyang
Shen, Zhennan
Xie, Rui
Zhang, Situo
Xie, Tianbao
Zhao, Zihan
Chen, Siyuan
Chen, Lu
Xu, Hongshen
Cao, Ruisheng
Yu, Kai
author_facet Zhang, Danyang
Shen, Zhennan
Xie, Rui
Zhang, Situo
Xie, Tianbao
Zhao, Zihan
Chen, Siyuan
Chen, Lu
Xu, Hongshen
Cao, Ruisheng
Yu, Kai
contents The Graphical User Interface (GUI) is pivotal for human interaction with the digital world, enabling efficient device control and the completion of complex tasks. Recent progress in Large Language Models (LLMs) and Vision Language Models (VLMs) offers the chance to create advanced GUI agents. To ensure their effectiveness, there's a pressing need for qualified benchmarks that provide trustworthy and reproducible evaluations -- a challenge current benchmarks often fail to address. To tackle this issue, we introduce Mobile-Env, a comprehensive toolkit tailored for creating GUI benchmarks in the Android mobile environment. Mobile-Env offers an isolated and controllable setting for reliable evaluations, and accommodates intermediate instructions and rewards to reflect real-world usage more naturally. Utilizing Mobile-Env, we collect an open-world task set across various real-world apps and a fixed world set, WikiHow, which captures a significant amount of dynamic online contents for fully controllable and reproducible evaluation. We conduct comprehensive evaluations of LLM agents using these benchmarks. Our findings reveal that even advanced models (e.g., GPT-4V and LLaMA-3) struggle with tasks that are relatively simple for humans. This highlights a crucial gap in current models and underscores the importance of developing more capable foundation models and more effective GUI agent frameworks.
format Preprint
id arxiv_https___arxiv_org_abs_2305_08144
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Mobile-Env: Building Qualified Evaluation Benchmarks for LLM-GUI Interaction
Zhang, Danyang
Shen, Zhennan
Xie, Rui
Zhang, Situo
Xie, Tianbao
Zhao, Zihan
Chen, Siyuan
Chen, Lu
Xu, Hongshen
Cao, Ruisheng
Yu, Kai
Artificial Intelligence
The Graphical User Interface (GUI) is pivotal for human interaction with the digital world, enabling efficient device control and the completion of complex tasks. Recent progress in Large Language Models (LLMs) and Vision Language Models (VLMs) offers the chance to create advanced GUI agents. To ensure their effectiveness, there's a pressing need for qualified benchmarks that provide trustworthy and reproducible evaluations -- a challenge current benchmarks often fail to address. To tackle this issue, we introduce Mobile-Env, a comprehensive toolkit tailored for creating GUI benchmarks in the Android mobile environment. Mobile-Env offers an isolated and controllable setting for reliable evaluations, and accommodates intermediate instructions and rewards to reflect real-world usage more naturally. Utilizing Mobile-Env, we collect an open-world task set across various real-world apps and a fixed world set, WikiHow, which captures a significant amount of dynamic online contents for fully controllable and reproducible evaluation. We conduct comprehensive evaluations of LLM agents using these benchmarks. Our findings reveal that even advanced models (e.g., GPT-4V and LLaMA-3) struggle with tasks that are relatively simple for humans. This highlights a crucial gap in current models and underscores the importance of developing more capable foundation models and more effective GUI agent frameworks.
title Mobile-Env: Building Qualified Evaluation Benchmarks for LLM-GUI Interaction
topic Artificial Intelligence
url https://arxiv.org/abs/2305.08144