arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2403.07718cs.LGcs.AI
收藏

WorkArena:Web智能体在解决常见知识工作任务上能力如何?

WorkArena: How Capable Are Web Agents at Solving Common Knowledge Work Tasks?

ServiceNow Research(ServiceNow研究院);Mila – Quebec AI Research Institute(米拉-魁北克人工智能研究所);Polytechnique Montréal(蒙特利尔理工学院);McGill University(麦吉尔大学);Université de Montréal(蒙特利尔大学)
Alexandre Drouin, Maxime Gasse, Massimo Caccia, Issam H. Laradji, Manuel Del Verme, Tom Marty, Léo Boisvert, Megh Thakkar, Quentin Cappart, David Vazquez, Nicol… 展开作者

Alexandre Drouin, Maxime Gasse, Massimo Caccia, Issam H. Laradji, Manuel Del Verme, Tom Marty, Léo Boisvert, Megh Thakkar, Quentin Cappart, David Vazquez, Nicolas Chapados, Alexandre Lacoste

AI总结:

针对Web智能体执行知识工作者日常企业软件任务的能力评估问题,提出基于ServiceNow平台的WorkArena基准与BrowserGym环境,实验表明当前智能体距完全自动化仍有差距,并揭示了开闭源LLM间的显著性能差异。

摘要:

我们研究使用基于大型语言模型(LLM)的智能体通过Web浏览器与软件进行交互。与先前工作不同,我们专注于衡量智能体执行任务的能力,这些任务涵盖了知识工作者利用企业软件系统进行的典型日常工作。为此,我们提出WorkArena,这是一个基于广泛使用的ServiceNow平台、包含33个任务的远程托管基准。我们还引入BrowserGym,一个用于此类智能体设计和评估的环境,提供丰富的动作集以及多模态观测。我们的实证评估显示,尽管当前智能体在WorkArena上展现出潜力,但距离实现完全任务自动化仍有相当大的差距。值得注意的是,我们的分析揭示了开源与闭源LLM之间存在显著的性能差异,突显了该领域未来探索和发展的关键领域。

英文摘要:

We study the use of large language model-based agents for interacting with software via web browsers. Unlike prior work, we focus on measuring the agents' ability to perform tasks that span the typical daily work of knowledge workers utilizing enterprise software systems. To this end, we propose WorkArena, a remote-hosted benchmark of 33 tasks based on the widely-used ServiceNow platform. We also introduce BrowserGym, an environment for the design and evaluation of such agents, offering a rich set of actions as well as multimodal observations. Our empirical evaluation reveals that while current agents show promise on WorkArena, there remains a considerable gap towards achieving full task automation. Notably, our analysis uncovers a significant performance disparity between open and closed-source LLMs, highlighting a critical area for future exploration and development in the field.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑