提出AI代理编排的设计框架与评估指标，助力构建可靠智能流程。
Design and Implementation of Agentic Orchestrations and Orchestration of Agents
- 构建代理编排的分类框架，涵盖任务特异性、可追踪性等核心属性。
- 设计量化评估指标，在光照预测场景中验证不同实现方案效果。
- 适合研究智能流程设计或部署企业级AI代理系统的开发者参考。
近年来，基于AI代理的业务流程管理日益受到关注。其前景在于通过结合流程技术，使以大语言模型为主的代理在保持自主性的同时，具备一定的鲁棒性、可管理性和可追溯性。本文提出一种针对代理编排选项的分类框架，依据任务特异性、可追溯性、可管理性、自主性与反应性、正确性保障等属性进行划分，并提供不同应用场景下的定性决策准则。同时，本文定义了用于量化评估实现特性的指标，并在预测性光照感知场景中展示了多种代理实现方式的应用。整体工作旨在为代理编排的设计与实现提供属性、准则与度量标准。
原文摘要 · Abstract (English)
Agentic Business Process Management has gained momentum recently. The prospect is that the autonomy of AI agents, i.e., predominantly LLM-based agents, can be balanced with a certain level of robustness, tractability, and traceability through a combination with process technology. In this paper, we provide a classification framework for agentic orchestration options along properties such as task specificity, traceability and tractability, autonomy and reactivity, and correctness assurance and present qualitative decision criteria for realizations of different scenarios. We also provide metrics for the quantitative assessment of realization properties and show them through different agentic implementations of a predictive light sensing scenario. Altogether, this work aims at providing properties, criteria, and metrics for the design and implementation of agentic orchestrations and orchestration of agents.
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。