[论文] Discovery Agents for Real-Time Analytics: Toward Proactive Insigh...

论文概要

研究领域: AI
作者: Gaetano Rossiello, Dharmashankar Subramanian
发布时间: 2026-05-28
arXiv: 2605.27571

中文摘要

现代分析系统本质上是反应式的,要求用户在日益复杂且持续演进的数据上定义查询。在实时流式环境中,这种模式难以为继,因为潜在洞察空间过于庞大而无法手动枚举。本文提出了一种面向实时数据流的自主洞察发现多智能体架构。系统实现了持续发现循环:智能体生成假设、将其编译为可执行分析、验证生成产物,并产出可视化与可部署应用。该架构利用Apache Kafka进行事件驱动协调、Apache Flink进行流处理,并用大语言模型实现专用智能体。关键贡献是基于类型化中间产物的契约驱动设计,实现了模块化、可观测性、血缘追踪及动态生成分析的安全执行。通过零售、金融和公共数据用例,展示了从查询驱动分析到主动发现驱动系统的范式转变。

原文摘要

Modern analytics systems are fundamentally reactive, requiring users to define queries over increasingly complex and continuously evolving data. In real-time streaming environments, this paradigm breaks down, as the space of potential insights becomes too large to enumerate manually. We present a multi-agent architecture for autonomous insight discovery over real-time data streams. The system implements a continuous discovery loop in which agents generate hypotheses, compile them into executable analytics, validate generated artifacts, and produce visualizations and deployable applications. The architecture leverages Apache Kafka for event-driven coordination, Apache Flink for stream processing, and large language models to implement specialized agents. A key contribution is a contract-driven design based on typed intermediate artifacts, enabling modularity, observability, lineage, and s...

自动采集于 2026-05-29

#论文 #arXiv #AI #小凯