Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2503.15937 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915810134458368 |
|---|---|
| author | Dai, Gaole Jiang, Shiqi Cao, Ting Li, Yuanchun Yang, Yuqing Tan, Rui Li, Mo Qiu, Lili |
| author_facet | Dai, Gaole Jiang, Shiqi Cao, Ting Li, Yuanchun Yang, Yuqing Tan, Rui Li, Mo Qiu, Lili |
| contents | We propose V-Droid, a mobile GUI task automation agent. Unlike previous mobile agents that utilize Large Language Models (LLMs) as generators to directly generate actions at each step, V-Droid employs LLMs as verifiers to evaluate candidate actions before making final decisions. To realize this novel paradigm, we introduce a comprehensive framework for constructing verifier-driven mobile agents: the discretized action space construction coupled with the prefilling-only workflow to accelerate the verification process, the pair-wise progress preference training to significantly enhance the verifier's decision-making capabilities, and the scalable human-agent joint annotation scheme to efficiently collect the necessary data at scale. V-Droid obtains a substantial task success rate across several public mobile task automation benchmarks: 59.5% on AndroidWorld, 38.3% on AndroidLab, and 49% on MobileAgentBench, surpassing existing agents by 5.2%, 2.1%, and 9%, respectively. Furthermore, V-Droid achieves a remarkably low latency of 4.3s per step, which is 6.1x faster compared with existing mobile agents. The source code is available at https://github.com/V-Droid-Agent/V-Droid. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_15937 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Advancing Mobile GUI Agents: A Verifier-Driven Approach to Practical Deployment Dai, Gaole Jiang, Shiqi Cao, Ting Li, Yuanchun Yang, Yuqing Tan, Rui Li, Mo Qiu, Lili Artificial Intelligence We propose V-Droid, a mobile GUI task automation agent. Unlike previous mobile agents that utilize Large Language Models (LLMs) as generators to directly generate actions at each step, V-Droid employs LLMs as verifiers to evaluate candidate actions before making final decisions. To realize this novel paradigm, we introduce a comprehensive framework for constructing verifier-driven mobile agents: the discretized action space construction coupled with the prefilling-only workflow to accelerate the verification process, the pair-wise progress preference training to significantly enhance the verifier's decision-making capabilities, and the scalable human-agent joint annotation scheme to efficiently collect the necessary data at scale. V-Droid obtains a substantial task success rate across several public mobile task automation benchmarks: 59.5% on AndroidWorld, 38.3% on AndroidLab, and 49% on MobileAgentBench, surpassing existing agents by 5.2%, 2.1%, and 9%, respectively. Furthermore, V-Droid achieves a remarkably low latency of 4.3s per step, which is 6.1x faster compared with existing mobile agents. The source code is available at https://github.com/V-Droid-Agent/V-Droid. |
| title | Advancing Mobile GUI Agents: A Verifier-Driven Approach to Practical Deployment |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2503.15937 |