TClone: Low-Latency Forking of Live GUI Environments for Computer-Use Agents
On the map: LLM agents and tool use → GUI and mobile agents
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in GUI and mobile agents, one of 16 directions in LLM agents and tool use. Builds on 9 of its 33 references that are in the map. First posted on arXiv 17 May 2026.
Builds on
9 of 33 references.
Closest ancestors · 2
Same direction, newest first
- 2024Agent S: An Open Agentic Framework that Uses Computers Like a Human10 Oct
- 2024OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments11 Apr
Other references · 7
- 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
- 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,155
- 2024SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineeringcited by 1,628
- 2025GTA1: GUI Test-time Scaling Agentcited by 102
- 2024GTA: A Benchmark for General Tool Agentscited by 77
- 2025Scaling Test-time Compute for LLM Agentscited by 59
- 2026Agent Alpha: Tree Search Unifying Generation, Exploration and Evaluation for Computer-Use Agentscited by 12
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026WeaveBench: A Long-Horizon, Real-World Benchmark for Computer-Use Agents with Hybrid Interfaces
- 2026TUA-Bench: A Benchmark for General-Purpose Terminal-Use Agents
- 2026Efficient GUI Agents: A Systems Survey of Observation, Memory, Action, and Runtime Optimization
- 2026EchoPath: Execution-Level Replayable Memory for GUI Agents
- 2026LegacyWorld: Atomicity-Aware Evaluation of GUI Agents for Legacy Workflows
- 2026JarvisGUI: Towards Cross-Device GUI Agents with Dynamic Task Composition
- 2026ChainWorld: Composing Long-Horizon Desktop Workloads from Atomic OSWorld Tasks
- 2026Desktop-Delta Bench: Do Computer-Use Models Understand Desktop GUI Transitions?