发表机构
PwC（普华永道）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出与框架无关的智能体配置管理（ACM）模型，经实验验证可实现异构智能体系统的管控等价表示，支持可复现性、可审计性等，适配LangGraph等主流框架。
AI 中文摘要
智能体系统越来越多地由异构智能体、提示词、工具、模型、技能、复合子系统、策略和执行工作流组成，其配置在不同框架和运行时环境中不断演变。现有的LLMOps和AgentOps平台支持编排和可观测性，但未提供通用的配置管控模型，以将这些系统表示并管控为一致的、可版本化的配置。本文介绍智能体配置管理（ACM），这是一个与框架无关的异构智能体系统的管控和配置参考模型。ACM结合了类型化且独立版本化的智能体配置项、不可变的修订版和基线、明确的配置-运行时分离、生命周期与保证语义、依赖感知的影响传播以及运行时溯源。异构原生配置通过语义投影被归一化为规范配置图，通用管控语义可在该图上运行。我们提供了一个Python参考实现，带有适用于LangGraph、CrewAI和OpenAI Agents SDK的适配器。评估结合了27种管控场景与9个定量影响传播案例。对于所评估的配置，这三个框架在投影后产生了管控等价的ACM表示和可复现的管控结果。影响语义被形式化为有限格上的单调传播，确立了初始影响估值之上最小不动点的收敛性、终止性和唯一性。这些结果证明，在评估范围内，通用管控语义可支持异构智能体执行抽象之间的可复现性、可审计性、依赖分析和互操作性。
英文摘要
Agentic systems are increasingly composed of heterogeneous agents, prompts, tools, models, skills, composite subsystems, policies, and execution workflows whose configurations evolve across frameworks and runtime environments. Existing LLMOps and AgentOps platforms support orchestration and observability but do not provide a common configuration-governance model for representing and governing these systems as coherent, versioned configurations. This paper introduces Agentic Configuration Management (ACM), a framework-independent governance and configuration reference model for heterogeneous agentic systems. ACM combines typed and independently versioned Agentic Configuration Items, immutable revisions and baselines, explicit configuration-runtime separation, lifecycle and assurance semantics, dependency-aware impact propagation, and runtime provenance. Heterogeneous native configurations are normalized through semantic projection into a canonical Configuration Graph on which common governance semantics operate. We provide a Python reference implementation with adapters for LangGraph, CrewAI, and the OpenAI Agents SDK. The evaluation combines 27 governance scenarios with nine quantitative impact-propagation cases. For the evaluated configurations, the three frameworks yield governance-equivalent ACM representations and reproducible governance outcomes after projection. The impact semantics are formalized as monotone propagation over a finite lattice, establishing convergence, termination, and uniqueness of the least fixed point above the initial impact valuation. These results provide evidence that common governance semantics can support reproducibility, auditability, dependency analysis, and interoperability across heterogeneous agentic execution abstractions within the evaluated scope.
Comments77 pages, 12 figures, 17 tables. Includes formal appendices and experimental evaluation across LangGraph, CrewAI, and the OpenAI Agents SDK. Reference implementation and evaluation artifacts: https://github.com/audreyqvial/ACM
