发表机构
ETH Zürich（苏黎世联邦理工学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对AI智能体观测与调控的界面缺失问题，研究人员推出AgentGUI，通过轨迹可视化、手动自动调控等功能提升智能体任务处理效率，成果已开源。
AI 中文摘要
AI智能体在处理复杂的长期运行任务方面能力日益增强。随着自主能力的快速提升，由于以人类为中心的界面有限，人类监督系统地滞后于智能体的发展。为解决这一问题，我们推出了AgentGUI，这是一个用户友好、本地托管的图形用户界面（GUI），用于在多个并发的长期会话中无缝观测与调控AI智能体。AgentGUI具有三大特性：1）丰富的智能体轨迹可视化功能；2）有效的手动与自动调控功能；3）与开源及前沿智能体框架的集成与协调功能。一项受控用户研究显示，该界面可将从智能体轨迹中识别关键元素的时间显著缩短38%（p=0.023）。在一项初步实验中，AgentGUI的自动漂移预防功能可使0.8B至9B模型阶梯范围内的小型本地智能体的任务完成率提升高达34个百分点（每个模型N=50次运行）。AgentGUI可通过其项目网站（this https URL）和开源代码库（this https URL）公开获取，同时还提供演示视频（this https URL）。
英文摘要
AI agents are increasingly adept at tackling complex, long-running tasks. With the rapid surge of autonomous capabilities, human oversight is systematically lagging behind due to limited human-centered interfacing. Aiming to address this, we introduce AgentGUI, a user-friendly, locally hosted GUI for seamlessly observing and steering AI agents amid multiple concurrent, long-running sessions. AgentGUI features 1) rich agent trajectory visualizations, 2) effective manual and automated steering, and 3) integration with and coordination between open-source and frontier agent frameworks. A controlled user study demonstrates statistically significant reduction in the time it takes to identify key elements from agent traces (38% faster, p = 0.023). In a preliminary experiment, AgentGUI's automated drift prevention feature raises the task completion rate of small local agents by as high as 34pp across a 0.8B--9B model ladder (N=50 runs per model). AgentGUI is publicly available through its project website (https://agent-gui-project.github.io) and open-source repository (https://github.com/eth-medical-ai-lab/agent-gui), along with a demo video (https://youtube.com/watch?v=GSDyxN1gTF0).
