Spine-Branch Coordination for Multi-agent Computer Use
Spine-Branch Coordination for Multi-agent Computer Use
View PDF HTML (experimental) Abstract: 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...
Spine-Branch 协同框架 (arXiv:2608.22077)
“View PDF HTML (experimental) Abstract: Computer use agents (CUAs) are increasingly deployed as multi-agent systems that decompose a task int”
Abstract: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.
| Subjects: | Computation and Language (cs.CL); Multiagent Systems (cs.MA) |
| Cite as: | arXiv:2608.22077 [cs.CL] |
| (or arXiv:2608.22077v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2608.22077 arXiv-issued DOI via DataCite |
Submission history
From: Mian Zhang [view email]
[v1]
Sat, 22 Aug 2026 18:48:37 UTC (1,087 KB)
Source: Agent Control Flash News · arxiv.org
Related Products & Analysis
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。
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。