提出脊干-分支架构，解决多虚拟机任务协作中的状态合并难题。
Spine-Branch Coordination for Multi-agent Computer Use
- 将任务拆分为脊干（持续状态）与分支（并行执行）结构
- 在200个长程任务上提升成功率6.0%~16.5%，成本降低34%~70%
- 适合需高效多机协同的自动化计算机使用场景
计算机使用代理（CUAs）正以多智能体系统形式部署，将任务分解为在多个并行虚拟机（VMs）上执行的子任务。然而，一个关键物理瓶颈是两个虚拟机的状态无法合并。以往系统对此采取非正式处理，而非将其视为核心问题。本文提出脊干-分支协调框架，将任务分解为‘脊干-分支’图结构：脊干承载主任务流并保持连续的虚拟机状态，分支任务并行执行以收集脊干完成任务所需信息。分支虚拟机在任务完成后即被丢弃，因此从不发生虚拟机合并。实验表明，在来自Odysseys数据集的200个长周期任务上，跨三种CUA基础架构，该方法相较基线系统成功率达6.0%~16.5%提升，且每任务成本降低34%~70%，证明显式建模虚拟机状态合并约束能有效支持多智能体计算机使用的高效扩展。
原文摘要 · Abstract (English)
Computer use agents (CUAs) are increasingly deployed as multi-agent systems that decompose a task into multiple subtasks executed across parallel virtual machines (VMs). However, a critical physical bottleneck is that the state of two VMs cannot be merged. Previous systems handle this ad-hoc rather than treating it as a first-class concern. We propose Spine-Branch Coordination for multi-agent computer use, a framework that decomposes a task into a "spine-branch" graph, where the spine carries the main task flow with continuous VM state and branch tasks execute in parallel to collect information the spine needs to complete the task. Branch VMs are discarded once their tasks finish, so no VM merging ever occurs. Experiments show that on 200 long-horizon tasks from Odysseys and across three CUA backbones, Spine-Branch improves success rate over the baseline system by 6.0% to 16.5%, while reducing per-task cost by 34% to 70%, indicating that explicitly modeling VM-state merging constraint enables multi-agent computer use to scale efficiently.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。