AgentBay: A Hybrid Interaction Sandbox for Seamless Human-AI Intervention in Agentic Systems

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Piao, Yun, Min, Hongbo, Su, Hang, Zhang, Leilei, Wang, Lei, Yin, Yue, Wu, Xiao, Xu, Zhejing, Qu, Liwei, Li, Hang, Zeng, Xinxin, Tian, Wei, Yu, Fei, Li, Xiaowei, Jiang, Jiayi, Liu, Tongxu, Tian, Hao, Que, Yufei, Tu, Xiaobing, Suo, Bing, Li, Yuebing, Chen, Xiangting, Zhao, Zeen, Tang, Jiaming, Huang, Wei, Li, Xuguang, Zhao, Jing, Li, Jin, Shen, Jie, Ren, Jinkui, Zhang, Xiantao
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908693666201600
author Piao, Yun
Min, Hongbo
Su, Hang
Zhang, Leilei
Wang, Lei
Yin, Yue
Wu, Xiao
Xu, Zhejing
Qu, Liwei
Li, Hang
Zeng, Xinxin
Tian, Wei
Yu, Fei
Li, Xiaowei
Jiang, Jiayi
Liu, Tongxu
Tian, Hao
Que, Yufei
Tu, Xiaobing
Suo, Bing
Li, Yuebing
Chen, Xiangting
Zhao, Zeen
Tang, Jiaming
Huang, Wei
Li, Xuguang
Zhao, Jing
Li, Jin
Shen, Jie
Ren, Jinkui
Zhang, Xiantao
author_facet Piao, Yun
Min, Hongbo
Su, Hang
Zhang, Leilei
Wang, Lei
Yin, Yue
Wu, Xiao
Xu, Zhejing
Qu, Liwei
Li, Hang
Zeng, Xinxin
Tian, Wei
Yu, Fei
Li, Xiaowei
Jiang, Jiayi
Liu, Tongxu
Tian, Hao
Que, Yufei
Tu, Xiaobing
Suo, Bing
Li, Yuebing
Chen, Xiangting
Zhao, Zeen
Tang, Jiaming
Huang, Wei
Li, Xuguang
Zhao, Jing
Li, Jin
Shen, Jie
Ren, Jinkui
Zhang, Xiantao
contents The rapid advancement of Large Language Models (LLMs) is catalyzing a shift towards autonomous AI Agents capable of executing complex, multi-step tasks. However, these agents remain brittle when faced with real-world exceptions, making Human-in-the-Loop (HITL) supervision essential for mission-critical applications. In this paper, we present AgentBay, a novel sandbox service designed from the ground up for hybrid interaction. AgentBay provides secure, isolated execution environments spanning Windows, Linux, Android, Web Browsers, and Code interpreters. Its core contribution is a unified session accessible via a hybrid control interface: An AI agent can interact programmatically via mainstream interfaces (MCP, Open Source SDK), while a human operator can, at any moment, seamlessly take over full manual control. This seamless intervention is enabled by Adaptive Streaming Protocol (ASP). Unlike traditional VNC/RDP, ASP is specifically engineered for this hybrid use case, delivering an ultra-low-latency, smoother user experience that remains resilient even in weak network environments. It achieves this by dynamically blending command-based and video-based streaming, adapting its encoding strategy based on network conditions and the current controller (AI or human). Our evaluation demonstrates strong results in security, performance, and task completion rates. In a benchmark of complex tasks, the AgentBay (Agent + Human) model achieved more than 48% success rate improvement. Furthermore, our ASP protocol reduces bandwidth consumption by up to 50% compared to standard RDP, and in end-to-end latency with around 5% reduction, especially under poor network conditions. We posit that AgentBay provides a foundational primitive for building the next generation of reliable, human-supervised autonomous systems.
format Preprint
id arxiv_https___arxiv_org_abs_2512_04367
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle AgentBay: A Hybrid Interaction Sandbox for Seamless Human-AI Intervention in Agentic Systems
Piao, Yun
Min, Hongbo
Su, Hang
Zhang, Leilei
Wang, Lei
Yin, Yue
Wu, Xiao
Xu, Zhejing
Qu, Liwei
Li, Hang
Zeng, Xinxin
Tian, Wei
Yu, Fei
Li, Xiaowei
Jiang, Jiayi
Liu, Tongxu
Tian, Hao
Que, Yufei
Tu, Xiaobing
Suo, Bing
Li, Yuebing
Chen, Xiangting
Zhao, Zeen
Tang, Jiaming
Huang, Wei
Li, Xuguang
Zhao, Jing
Li, Jin
Shen, Jie
Ren, Jinkui
Zhang, Xiantao
Artificial Intelligence
The rapid advancement of Large Language Models (LLMs) is catalyzing a shift towards autonomous AI Agents capable of executing complex, multi-step tasks. However, these agents remain brittle when faced with real-world exceptions, making Human-in-the-Loop (HITL) supervision essential for mission-critical applications. In this paper, we present AgentBay, a novel sandbox service designed from the ground up for hybrid interaction. AgentBay provides secure, isolated execution environments spanning Windows, Linux, Android, Web Browsers, and Code interpreters. Its core contribution is a unified session accessible via a hybrid control interface: An AI agent can interact programmatically via mainstream interfaces (MCP, Open Source SDK), while a human operator can, at any moment, seamlessly take over full manual control. This seamless intervention is enabled by Adaptive Streaming Protocol (ASP). Unlike traditional VNC/RDP, ASP is specifically engineered for this hybrid use case, delivering an ultra-low-latency, smoother user experience that remains resilient even in weak network environments. It achieves this by dynamically blending command-based and video-based streaming, adapting its encoding strategy based on network conditions and the current controller (AI or human). Our evaluation demonstrates strong results in security, performance, and task completion rates. In a benchmark of complex tasks, the AgentBay (Agent + Human) model achieved more than 48% success rate improvement. Furthermore, our ASP protocol reduces bandwidth consumption by up to 50% compared to standard RDP, and in end-to-end latency with around 5% reduction, especially under poor network conditions. We posit that AgentBay provides a foundational primitive for building the next generation of reliable, human-supervised autonomous systems.
title AgentBay: A Hybrid Interaction Sandbox for Seamless Human-AI Intervention in Agentic Systems
topic Artificial Intelligence
url https://arxiv.org/abs/2512.04367