中文标题#
阿尔法伯克利：一种用于代理系统编排的可扩展框架
英文标题#
Alpha Berkeley: A Scalable Framework for the Orchestration of Agentic Systems
中文摘要#
在科学设施、工业工厂和能源基础设施等安全关键环境中，协调异构控制系统之间的工作流程仍然是一个核心挑战。语言模型驱动的代理为这些任务提供了一个自然的接口，但现有方法通常缺乏可扩展性、可靠性和人工监督。我们引入了 Alpha Berkeley 框架，这是一个可用于生产的架构，用于可扩展的代理系统，该系统将对话上下文与强大的工具编排相结合。该框架具有动态能力分类，可根据任务选择相关工具，一种先计划后编排的模型，可以生成具有显式依赖关系并可选人工批准的执行计划，上下文感知的任务提取，结合对话历史与外部记忆和领域资源，以及具备检查点、工件管理和模块化部署的生产就绪执行环境。我们通过两个案例研究展示了其多功能性：一个教程风格的风力发电场监控示例和在先进光源粒子加速器上的部署。这些结果确立了 Alpha Berkeley 作为高风险领域代理系统的一个可靠且透明的框架。
英文摘要#
Coordinating workflows across heterogeneous control systems remains a central challenge in safety-critical environments such as scientific facilities, industrial plants, and energy infrastructures. Language-model-driven agents offer a natural interface for these tasks, but existing approaches often lack scalability, reliability, and human oversight. We introduce the Alpha Berkeley Framework, a production-ready architecture for scalable agentic systems that integrate conversational context with robust tool orchestration. The framework features dynamic capability classification to select only relevant tools per task, a plan-first orchestration model that generates execution plans with explicit dependencies and optional human approval, context-aware task extraction that combines dialogue history with external memory and domain resources, and production-ready execution environments with checkpointing, artifact management, and modular deployment. We demonstrate its versatility through two case studies: a tutorial-style wind farm monitoring example and a deployment at the Advanced Light Source particle accelerator. These results establish Alpha Berkeley as a reliable and transparent framework for agentic systems in high-stakes domains.
文章页面#
PDF 获取#
抖音扫码查看更多精彩内容