构建企业级复合AI架构，用流水线协调智能体与数据。
Orchestrating Agents and Data for Enterprise: A Blueprint Architecture for Compound AI
- 以'流'为核心，统一调度智能体间的数据与指令流动。
- 通过注册表管理企业私有模型、数据和API，支持多模态数据调用。
- 适合需整合内部资源的AI系统开发者，尤其关注成本与响应速度的企业。
大型语言模型（LLMs）在工业界因广泛任务能力而备受关注，但其广泛应用面临挑战：如何集成现有应用与基础设施、利用企业私有数据/模型/API，以及满足成本、质量、响应速度等要求。为此，行业正从单一模型转向复合AI系统，以实现更强大、灵活和可靠的智能应用。然而，当前进展分散，缺乏整体架构蓝图。本文提出一种面向企业应用的复合AI系统‘蓝图架构’，核心是通过‘流’来协调智能体间的数据与指令流动。企业内部的私有模型与API被映射为‘智能体’，存于‘智能体注册表’中，提供元数据与可检索表示以支持搜索与规划；数据通过‘数据注册表’进行多模态管理；任务与数据规划器则根据服务质量（QoS）要求（如成本、精度、延迟）对任务进行分解、映射与优化。我们以人力资源领域为例展示了该架构的实现，并讨论了企业级代理AI的发展机遇与挑战。
原文摘要 · Abstract (English)
Large language models (LLMs) have gained significant interest in industry due to their impressive capabilities across a wide range of tasks. However, the widespread adoption of LLMs presents several challenges, such as integration into existing applications and infrastructure, utilization of company proprietary data, models, and APIs, and meeting cost, quality, responsiveness, and other requirements. To address these challenges, there is a notable shift from monolithic models to compound AI systems, with the premise of more powerful, versatile, and reliable applications. However, progress thus far has been piecemeal, with proposals for agentic workflows, programming models, and extended LLM capabilities, without a clear vision of an overall architecture. In this paper, we propose a 'blueprint architecture' for compound AI systems for orchestrating agents and data for enterprise applications. In our proposed architecture the key orchestration concept is 'streams' to coordinate the flow of data and instructions among agents. Existing proprietary models and APIs in the enterprise are mapped to 'agents', defined in an 'agent registry' that serves agent metadata and learned representations for search and planning. Agents can utilize proprietary data through a 'data registry' that similarly registers enterprise data of various modalities. Tying it all together, data and task 'planners' break down, map, and optimize tasks and queries for given quality of service (QoS) requirements such as cost, accuracy, and latency. We illustrate an implementation of the architecture for a use-case in the HR domain and discuss opportunities and challenges for 'agentic AI' in the enterprise.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。