Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zheng, Longtao, Huang, Zhiyuan, Xue, Zhenghai, Wang, Xinrun, An, Bo, Yan, Shuicheng
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2403.17918
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866929714526945280
author Zheng, Longtao
Huang, Zhiyuan
Xue, Zhenghai
Wang, Xinrun
An, Bo
Yan, Shuicheng
author_facet Zheng, Longtao
Huang, Zhiyuan
Xue, Zhenghai
Wang, Xinrun
An, Bo
Yan, Shuicheng
contents General virtual agents need to handle multimodal observations, master complex action spaces, and self-improve in dynamic, open-domain environments. However, existing environments are often domain-specific and require complex setups, which limits agent development and evaluation in real-world settings. As a result, current evaluations lack in-depth analyses that decompose fundamental agent capabilities. We introduce AgentStudio, a trinity of environments, tools, and benchmarks to address these issues. AgentStudio provides a lightweight, interactive environment with highly generic observation and action spaces, e.g., video observations and GUI/API actions. It integrates tools for creating online benchmark tasks, annotating GUI elements, and labeling actions in videos. Based on our environment and tools, we curate an online task suite that benchmarks both GUI interactions and function calling with efficient auto-evaluation. We also reorganize existing datasets and collect new ones using our tools to establish three datasets: GroundUI, IDMBench, and CriticBench. These datasets evaluate fundamental agent abilities, including GUI grounding, learning from videos, and success detection, pointing to the desiderata for robust, general, and open-ended virtual agents.
format Preprint
id arxiv_https___arxiv_org_abs_2403_17918
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle AgentStudio: A Toolkit for Building General Virtual Agents
Zheng, Longtao
Huang, Zhiyuan
Xue, Zhenghai
Wang, Xinrun
An, Bo
Yan, Shuicheng
Artificial Intelligence
General virtual agents need to handle multimodal observations, master complex action spaces, and self-improve in dynamic, open-domain environments. However, existing environments are often domain-specific and require complex setups, which limits agent development and evaluation in real-world settings. As a result, current evaluations lack in-depth analyses that decompose fundamental agent capabilities. We introduce AgentStudio, a trinity of environments, tools, and benchmarks to address these issues. AgentStudio provides a lightweight, interactive environment with highly generic observation and action spaces, e.g., video observations and GUI/API actions. It integrates tools for creating online benchmark tasks, annotating GUI elements, and labeling actions in videos. Based on our environment and tools, we curate an online task suite that benchmarks both GUI interactions and function calling with efficient auto-evaluation. We also reorganize existing datasets and collect new ones using our tools to establish three datasets: GroundUI, IDMBench, and CriticBench. These datasets evaluate fundamental agent abilities, including GUI grounding, learning from videos, and success detection, pointing to the desiderata for robust, general, and open-ended virtual agents.
title AgentStudio: A Toolkit for Building General Virtual Agents
topic Artificial Intelligence
url https://arxiv.org/abs/2403.17918