Skip to content
Source
Agent Control Flash News·· 2h agoAI Score35

TClone: Low-Latency Forking of Live GUI Environments for Computer-Use Agents

TClone: Low-Latency Forking of Live GUI Environments for Computer-Use Agents

Edge-TTS Studio Audio
Free for all listeners
Click to synthesize audio
00:00
00:00
AI Overview

View PDF HTML (experimental) Abstract: Computer-use agents increasingly operate inside live personal workspaces, where their actions can modify files, applications, GUI state, credentials, and authenticated sessions. This creates a tension between safety and quality: agents...

Primary Source
Academic Paper·arXiv:2605.17320

TClone (arXiv:2605.17320)

“View PDF HTML (experimental) Abstract: Computer-use agents increasingly operate inside live personal workspaces, where their actions can mod”

Body

View PDF HTML (experimental)

Abstract:Computer-use agents increasingly operate inside live personal workspaces, where their actions can modify files, applications, GUI state, credentials, and authenticated sessions. This creates a tension between safety and quality: agents need isolation and rollback to avoid damaging user state, but also need fast branching to support speculative execution and parallel search. Existing VMs, containers, and checkpoint/restore systems can isolate or recover workloads, but they do not provide low-latency versioning of a full interactive workspace.
We present TClone, a forkable personal workspace system for computer-use agents. TClone enables a live GUI workspace to be snapshotted, forked into isolated branches, rolled back, and selectively committed or merged. Its design separates fast branch creation from durable checkpointing, using sibling containers, copy-on-write memory sharing, filesystem versioning, GUI-local execution, and asynchronous checkpointing. In our end-to-end agent-loop measurement, TClone reduces total task latency by 1.9x and 1.5x over KVM and CRIU. By making workspace versioning a first-class systems primitive, TClone supports safer and higher-quality agent execution over real personal computing environments.
Subjects: Operating Systems (cs.OS); Artificial Intelligence (cs.AI)
Cite as: arXiv:2605.17320 [cs.OS]
  (or arXiv:2605.17320v1 [cs.OS] for this version)
  https://doi.org/10.48550/arXiv.2605.17320

arXiv-issued DOI via DataCite

Submission history

From: Yiying Zhang [view email]
[v1] Sun, 17 May 2026 08:24:01 UTC (2,442 KB)

Source: Agent Control Flash News · arxiv.org

Related Products & Analysis

Original·站长/Quantara 团队·~3 min read

Cursor Agent 架构全景拆解:从影子工作区到多文件推演引擎

全面剖析 Cursor 在 Agent 模式下的底层技术实现,解析影子分支隔离、LSP 上下文剪枝以及预测性补全的核心架构细节与工程实践经验。

Underlying architectures & industry dynamicsRead Analysis →
Curated·Vercel Changelog·~1 min read

Vercel v0 推出全新多 Agent 协作画布与实时全栈部署预览

动态速评:v0 正在从单一组件生成器演进为全栈应用搭建协作台,尤其是与 Neon/Postgres 的直连极大降低了全栈原型验证成本。

Underlying architectures & industry dynamicsRead Analysis →