Agentic Configuration Management (ACM): A Reference Configuration Model for Governed Agentic Systems
2026-08-11 • Software Engineering
Software Engineering
AI summaryⓘ
The authors present Agentic Configuration Management (ACM), a system that helps organize and govern complex setups made of different kinds of agents, tools, and workflows. Unlike current tools, ACM offers a unified way to manage and track versions of these components independently while keeping configurations and runtime separate. They tested ACM with three different agent frameworks and showed it produces the same governance results, proving it can work across various systems. Their method also ensures consistent tracking of changes and dependencies, making it easier to audit and reproduce system behavior.
Agentic systemsConfiguration managementVersion controlDependency analysisGovernanceImmutable revisionsRuntime provenanceSemantic projectionConfiguration graphImpact propagation
Authors
Audrey Quessada-Vial
Abstract
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.