SPA-Bench: A Comprehensive Benchmark for SmartPhone Agent Evaluation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908292270260224 |
|---|---|
| author | Chen, Jingxuan Yuen, Derek Xie, Bin Yang, Yuhao Chen, Gongwei Wu, Zhihao Yixing, Li Zhou, Xurui Liu, Weiwen Wang, Shuai Zhou, Kaiwen Shao, Rui Nie, Liqiang Wang, Yasheng Hao, Jianye Wang, Jun Shao, Kun |
| author_facet | Chen, Jingxuan Yuen, Derek Xie, Bin Yang, Yuhao Chen, Gongwei Wu, Zhihao Yixing, Li Zhou, Xurui Liu, Weiwen Wang, Shuai Zhou, Kaiwen Shao, Rui Nie, Liqiang Wang, Yasheng Hao, Jianye Wang, Jun Shao, Kun |
| contents | Smartphone agents are increasingly important for helping users control devices efficiently, with (Multimodal) Large Language Model (MLLM)-based approaches emerging as key contenders. Fairly comparing these agents is essential but challenging, requiring a varied task scope, the integration of agents with different implementations, and a generalisable evaluation pipeline to assess their strengths and weaknesses. In this paper, we present SPA-Bench, a comprehensive SmartPhone Agent Benchmark designed to evaluate (M)LLM-based agents in an interactive environment that simulates real-world conditions. SPA-Bench offers three key contributions: (1) A diverse set of tasks covering system and third-party apps in both English and Chinese, focusing on features commonly used in daily routines; (2) A plug-and-play framework enabling real-time agent interaction with Android devices, integrating over ten agents with the flexibility to add more; (3) A novel evaluation pipeline that automatically assesses agent performance across multiple dimensions, encompassing seven metrics related to task completion and resource consumption. Our extensive experiments across tasks and agents reveal challenges like interpreting mobile user interfaces, action grounding, memory retention, and execution costs. We propose future research directions to ease these difficulties, moving closer to real-world smartphone agent applications. SPA-Bench is available at https://ai-agents-2030.github.io/SPA-Bench/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_15164 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | SPA-Bench: A Comprehensive Benchmark for SmartPhone Agent Evaluation Chen, Jingxuan Yuen, Derek Xie, Bin Yang, Yuhao Chen, Gongwei Wu, Zhihao Yixing, Li Zhou, Xurui Liu, Weiwen Wang, Shuai Zhou, Kaiwen Shao, Rui Nie, Liqiang Wang, Yasheng Hao, Jianye Wang, Jun Shao, Kun Artificial Intelligence Smartphone agents are increasingly important for helping users control devices efficiently, with (Multimodal) Large Language Model (MLLM)-based approaches emerging as key contenders. Fairly comparing these agents is essential but challenging, requiring a varied task scope, the integration of agents with different implementations, and a generalisable evaluation pipeline to assess their strengths and weaknesses. In this paper, we present SPA-Bench, a comprehensive SmartPhone Agent Benchmark designed to evaluate (M)LLM-based agents in an interactive environment that simulates real-world conditions. SPA-Bench offers three key contributions: (1) A diverse set of tasks covering system and third-party apps in both English and Chinese, focusing on features commonly used in daily routines; (2) A plug-and-play framework enabling real-time agent interaction with Android devices, integrating over ten agents with the flexibility to add more; (3) A novel evaluation pipeline that automatically assesses agent performance across multiple dimensions, encompassing seven metrics related to task completion and resource consumption. Our extensive experiments across tasks and agents reveal challenges like interpreting mobile user interfaces, action grounding, memory retention, and execution costs. We propose future research directions to ease these difficulties, moving closer to real-world smartphone agent applications. SPA-Bench is available at https://ai-agents-2030.github.io/SPA-Bench/. |
| title | SPA-Bench: A Comprehensive Benchmark for SmartPhone Agent Evaluation |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2410.15164 |