WorkArena: How Capable Are Web Agents at Solving Common Knowledge Work Tasks?
This work addresses the challenge of automating daily knowledge work tasks for enterprise users, but it is incremental as it builds on prior web agent research by focusing on a specific domain.
The authors tackled the problem of evaluating large language model-based agents' ability to perform knowledge work tasks on enterprise software, finding that current agents show promise but have a considerable gap towards full automation, with a significant performance disparity between open and closed-source models.
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.