发表机构
Nexilume Research（Nexilume研究院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
Nexus提出一种云-边缘执行架构，将智能体调用视为持久任务，通过分布式运行时、运行范围委托和持久记录，实现跨设备可靠执行并降低开销。
AI 中文摘要
语言模型智能体正在演变为与模型、工具、计算机、移动设备和分布式环境交互的长期运行服务。现有智能体框架简化了推理和工具调用，但以云为中心的设计面临三个限制：集中式执行增加了故障影响、扩展压力和计算成本；将智能体扩展到计算机、移动设备和边缘环境需要统一的执行抽象和权限控制；长期运行需要跨故障、恢复、结果、使用和结算的一致生命周期管理。我们提出Nexus，一个云-边缘平台，将每次调用视为持久任务。Nexus使用基于OpenWrt的运行时进行分布式服务，使用运行范围委托对计算机和移动环境进行授权访问，并使用持久记录跟踪云和边缘组件间的执行、输出、故障、恢复、使用和计费。我们在受控、跨设备和模型驱动的工作负载上评估Nexus。所有十个Computer-Android工作流均成功，所有六个撤销测试阻止后续写入同时保留先前授权的读取。在工作者丢失下，日志记录消除了重复追加（每任务从六次降至零次），增加了0.933秒的平均正常路径开销。在24个匹配任务对中，Nexus完成24个任务，而Dify完成22个，在共同成功的对中中位数快3.88秒。在另一工作负载中，Nexus在比Dapr更小的测试增量运行时内存上限下运行（16对64 MiB），尽管Dapr实现了更低的成功调用延迟。这些结果展示了局部性、操作范围权限和持久结果身份如何支持具有工作负载相关成本的云-边缘智能体服务。
英文摘要
Language-model agents are evolving into long-running services that interact with models, tools, computers, mobile devices, and distributed environments. Existing agent frameworks simplify reasoning and tool invocation. However, cloud-centric designs face three limitations: centralized execution increases failure impact, scaling pressure, and compute cost; extending agents across computers, mobile devices, and edge environments requires a unified execution abstraction with permission control; and long-running executions require consistent lifecycle management across failures, recovery, results, usage, and settlement. We present Nexus, a cloud-edge platform that treats each invocation as a persistent task. Nexus uses an OpenWrt-based runtime for distributed serving, run-scoped delegation for authorized access to Computer and Mobile environments, and persistent records to track execution, outputs, failures, recovery, usage, and charging across cloud and edge components. We evaluate Nexus on controlled, cross-device, and model-driven workloads. All ten Computer-Android workflows succeed, and all six revocation tests block subsequent writes while preserving prior authorized reads. Under worker loss, journaling eliminates duplicate appends (six to zero per task), adding 0.933 s mean normal-path overhead. Across 24 matched task pairs, Nexus completes 24 tasks versus Dify's 22 and is a median 3.88 s faster on jointly successful pairs. In a separate workload, Nexus operates under a smaller tested incremental-runtime memory ceiling than Dapr (16 versus 64 MiB), although Dapr achieves lower successful-call latency. These results demonstrate how locality, operation-scoped authority, and persistent result identity support cloud-edge agent services with workload-dependent costs.
