Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2412.18116 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910928751034368 |
|---|---|
| author | Wen, Hao Tian, Shizuo Pavlov, Borislav Du, Wenjie Li, Yixuan Chang, Ge Zhao, Shanhui Liu, Jiacheng Liu, Yunxin Zhang, Ya-Qin Li, Yuanchun |
| author_facet | Wen, Hao Tian, Shizuo Pavlov, Borislav Du, Wenjie Li, Yixuan Chang, Ge Zhao, Shanhui Liu, Jiacheng Liu, Yunxin Zhang, Ya-Qin Li, Yuanchun |
| contents | Large language models (LLMs) have brought exciting new advances to mobile UI agents, a long-standing research field that aims to complete arbitrary natural language tasks through mobile UI interactions. However, existing UI agents usually demand powerful large language models that are difficult to be deployed locally on end-users' devices, raising huge concerns about user privacy and centralized serving cost. Inspired by the remarkable coding abilities of recent small language models (SLMs), we propose to convert the UI task automation problem to a code generation problem, which can be effectively solved by an on-device SLM and efficiently executed with an on-device code interpreter. Unlike normal coding tasks that can be extensively pre-trained with public datasets, generating UI automation code is challenging due to the diversity, complexity, and variability of target apps. Therefore, we adopt a document-centered approach that automatically builds fine-grained API documentation for each app and generates diverse task samples based on this documentation. By guiding the agent with the synthetic documents and task samples, it learns to generate precise and efficient scripts to complete unseen tasks. Based on detailed comparisons with state-of-the-art mobile UI agents, our approach effectively improves the mobile task automation with significantly higher success rates and lower latency/token consumption. Code is open-sourced at https://github.com/MobileLLM/AutoDroid-V2. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_18116 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | AutoDroid-V2: Boosting SLM-based GUI Agents via Code Generation Wen, Hao Tian, Shizuo Pavlov, Borislav Du, Wenjie Li, Yixuan Chang, Ge Zhao, Shanhui Liu, Jiacheng Liu, Yunxin Zhang, Ya-Qin Li, Yuanchun Artificial Intelligence Large language models (LLMs) have brought exciting new advances to mobile UI agents, a long-standing research field that aims to complete arbitrary natural language tasks through mobile UI interactions. However, existing UI agents usually demand powerful large language models that are difficult to be deployed locally on end-users' devices, raising huge concerns about user privacy and centralized serving cost. Inspired by the remarkable coding abilities of recent small language models (SLMs), we propose to convert the UI task automation problem to a code generation problem, which can be effectively solved by an on-device SLM and efficiently executed with an on-device code interpreter. Unlike normal coding tasks that can be extensively pre-trained with public datasets, generating UI automation code is challenging due to the diversity, complexity, and variability of target apps. Therefore, we adopt a document-centered approach that automatically builds fine-grained API documentation for each app and generates diverse task samples based on this documentation. By guiding the agent with the synthetic documents and task samples, it learns to generate precise and efficient scripts to complete unseen tasks. Based on detailed comparisons with state-of-the-art mobile UI agents, our approach effectively improves the mobile task automation with significantly higher success rates and lower latency/token consumption. Code is open-sourced at https://github.com/MobileLLM/AutoDroid-V2. |
| title | AutoDroid-V2: Boosting SLM-based GUI Agents via Code Generation |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2412.18116 |