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#
在科學設施、工業工廠和能源基礎設施等安全關鍵環境中，協調異構控制系統之間的工作流程仍然是一個核心挑戰。語言模型驅動的代理為這些任務提供了一個自然的接口，但現有方法通常缺乏可擴展性、可靠性和人工監督。我們引入了 Alpha Berkeley 框架，這是一個可用於生產的架構，用於可擴展的代理系統，該系統將對話上下文與強大的工具編排相結合。該框架具有動態能力分類，可根據任務選擇相關工具，一種先計劃後編排的模型，可以生成具有顯式依賴關係並可選人工批准的執行計劃，上下文感知的任務提取，結合對話歷史與外部記憶和領域資源，以及具備檢查點、工件管理和模塊化部署的生產就緒執行環境。我們通過兩個案例研究展示了其多功能性：一個教程風格的風力發電場監控示例和在先進光源粒子加速器上的部署。這些結果確立了 Alpha Berkeley 作為高風險領域代理系統的一個可靠且透明的框架。
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