AgentTrek: Agent Trajectory Synthesis via Guiding Replay with Web Tutorials

Uloženo v:
Podrobná bibliografie
Vydáno v:arXiv.org (Dec 12, 2024), p. n/a
Hlavní autor: Xu, Yiheng
Další autoři: Lu, Dunjie, Shen, Zhennan, Wang, Junli, Wang, Zekun, Mao, Yuchen, Xiong, Caiming, Yu, Tao
Vydáno:
Cornell University Library, arXiv.org
Témata:
On-line přístup:Citation/Abstract
Full text outside of ProQuest
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

MARC

LEADER 00000nab a2200000uu 4500
001 3144198202
003 UK-CbPIL
022 |a 2331-8422 
035 |a 3144198202 
045 0 |b d20241212 
100 1 |a Xu, Yiheng 
245 1 |a AgentTrek: Agent Trajectory Synthesis via Guiding Replay with Web Tutorials 
260 |b Cornell University Library, arXiv.org  |c Dec 12, 2024 
513 |a Working Paper 
520 3 |a Graphical User Interface (GUI) agents hold great potential for automating complex tasks across diverse digital environments, from web applications to desktop software. However, the development of such agents is hindered by the lack of high-quality, multi-step trajectory data required for effective training. Existing approaches rely on expensive and labor-intensive human annotation, making them unsustainable at scale. To address this challenge, we propose AgentTrek, a scalable data synthesis pipeline that generates high-quality GUI agent trajectories by leveraging web tutorials. Our method automatically gathers tutorial-like texts from the internet, transforms them into task goals with step-by-step instructions, and employs a visual-language model agent to simulate their execution in a real digital environment. A VLM-based evaluator ensures the correctness of the generated trajectories. We demonstrate that training GUI agents with these synthesized trajectories significantly improves their grounding and planning performance over the current models. Moreover, our approach is more cost-efficient compared to traditional human annotation methods. This work underscores the potential of guided replay with web tutorials as a viable strategy for large-scale GUI agent training, paving the way for more capable and autonomous digital agents. 
653 |a User interface 
653 |a Visual tasks 
653 |a Graphical user interface 
653 |a Annotations 
653 |a Applications programs 
653 |a Synthesis 
653 |a Online tutorials 
653 |a Trajectory planning 
653 |a Task complexity 
653 |a Training 
700 1 |a Lu, Dunjie 
700 1 |a Shen, Zhennan 
700 1 |a Wang, Junli 
700 1 |a Wang, Zekun 
700 1 |a Mao, Yuchen 
700 1 |a Xiong, Caiming 
700 1 |a Yu, Tao 
773 0 |t arXiv.org  |g (Dec 12, 2024), p. n/a 
786 0 |d ProQuest  |t Engineering Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3144198202/abstract/embedded/6A8EOT78XXH2IG52?source=fedsrch 
856 4 0 |3 Full text outside of ProQuest  |u http://arxiv.org/abs/2412.09605