发表机构
University of Cyprus（塞浦路斯大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
AgentWare提出AgenticOps框架，自动化边缘到云环境中智能体应用的配置、部署、可观测性与评估，显著降低人工成本。
AI 中文摘要
在边缘到云连续体中部署基于LLM的智能体应用，由于硬件异构性、部署复杂性、可观测性有限以及缺乏系统性评估方法，仍然具有挑战性。现有解决方案分别处理智能体开发、可观测性或基准测试，对分布式智能体应用的全生命周期支持有限。本文提出了AgentWare，一个AgenticOps框架，可自动化智能体应用在边缘到云基础设施上的配置、部署、可观测性和评估。AgentWare引入了一个端到端的生命周期管道，自动准备异构执行环境，将用户定义的智能体实现转换为分布式应用，在连续体中部署智能体组件，并统一收集执行轨迹、基础设施遥测和评估指标。该框架进一步通过LLM-as-a-Judge工作流支持自动化语义评估，并生成涵盖正确性、性能、资源利用率和能耗的可复现报告。我们通过一个部署在真实边缘到云基础设施上的分布式图书助手智能体，在多种部署和模型配置下展示了AgentWare的适用性。结果表明，AgentWare能够实现分布式智能体应用的系统性实验和评估，同时显著减少部署、仪器化和分析所需的人工工作量。
英文摘要
Deploying LLM-enabled agentic applications across the Edge-to-Cloud continuum remains challenging due to hardware heterogeneity, deployment complexity, limited observability, and the lack of systematic evaluation methods. Existing solutions address agent development, observability, or benchmarking separately, offering limited support for the full lifecycle of distributed agentic applications. This paper presents AgentWare, an AgenticOps framework that automates the provisioning, deployment, observability, and evaluation of agentic applications across Edge-to-Cloud infrastructures. AgentWare introduces an end-to-end lifecycle pipeline that automatically prepares heterogeneous execution environments, transforms user-defined agent implementations into distributed applications, deploys agent components across the continuum, and performs unified collection of execution traces, infrastructure telemetry, and evaluation metrics. The framework further supports automated semantic evaluation through LLM-as-a-Judge workflows and generates reproducible reports covering correctness, performance, resource utilization, and energy consumption. We demonstrate the applicability of AgentWare through a distributed book assistant agent deployed across real Edge-to-Cloud infrastructure under multiple deployment and model configurations. The results show that AgentWare enables systematic experimentation and evaluation of distributed agentic applications while significantly reducing the manual effort required for deployment, instrumentation, and analysis.
CommentsAccepted for publication at the 17th International Conference on Cloud Computing Technology and Science (IEEE CloudCom 2026)
