paper-with-me

홈 › Papers

AgentGUI: An Interface for Observing and Steering Long-Running AI Agents

2026-07-28 · Xuan Zhao, Jiwoong Sohn, Qinyue Zheng, Michael Moor arxiv

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).

📄 PDF Abstract BibTeX arXiv:2607.26300

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

AdaLens: Interactive Storyline for Monitoring and Steering Long-Running Agentic Data Analysis

2026-08-18 · Yangtian Liu, Yan Miao, Shuhan Liu, Yunfan Zhou 외 arxiv

Large language models are pushing data science toward increasingly autonomous and agentic workflows, with recent systems already supporting multi-step and long-running analyses. As these workflows become more autonomous,…

Gaze Training by Modulated Dropout Improves Imitation Learning

2019-04-17 · Yuying Chen, Congcong Liu, Lei Tai, Ming Liu 외

Imitation learning by behavioral cloning is a prevalent method that has achieved some success in vision-based autonomous driving. The basic idea behind behavioral cloning is to have the neural network learn from observin…

Autonomous DrivingImitation Learning

NegotiationGym: Self-Optimizing Agents in a Multi-Agent Social Simulation Environment

2025-10-05 · Shashank Mangla, Chris Hokamp, Jack Boylan, Demian Gholipour Ghalandari 외 arxiv

We design and implement NegotiationGym, an API and user interface for configuring and running multi-agent social simulations focused upon negotiation and cooperation. The NegotiationGym codebase offers a user-friendly, c…

The Anatomy of Alignment: Decomposing Preference Optimization by Steering Sparse Features

2025-09-16 · Jeremias Ferrao, Matthijs van der Lende, Ilija Lichkovski, Clement Neo arxiv

Prevailing alignment methods induce opaque parameter changes, obscuring what models truly learn. To address this, we introduce Feature Steering with Reinforcement Learning (FSRL), a framework that trains a lightweight ad…

Reinforcement Learning

Cognitive Steering in Deep Neural Networks via Long-Range Modulatory Feedback Connections

2023-09-21 · NeurIPS 2023 11

Given the rich visual information available in each glance, humans can internally direct their visual attention to enhance goal-relevant information---a capacity often absent in standard vision models. Here we introduce…