Architecting AgentOps Needs CHANGE

2026-01-10

arXiv.org

AI Summary

Traditional DevOps and MLOps struggle to ensure runtime reliability of Agentic AI systems in non-deterministic, continuously evolving environments. This work proposes a novel operations paradigm tailored to the full lifecycle of Agentic AI, centered on the pioneering CHANGE framework—encompassing six core capabilities: Contextualize, Harmonize, Anticipate, Negotiate, Generate, and Evolve—to enable dynamic co-adaptation among agents, infrastructure, and human oversight. The AgentOps platform, built upon this framework, demonstrates its effectiveness in a customer service scenario by reliably supporting the continuous evolution of Agentic AI systems. This approach establishes an innovative architectural foundation for operating non-deterministic agent-based systems, addressing critical gaps in current AI运维 practices.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Multiagent Systems: Agent/AI Theories and Architectures
• Humans and AI: Planning and Decision Support for Human-Machine Teams

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

The emergence of Agentic AI systems has outpaced the architectural thinking required to operate them effectively. These agents differ fundamentally from traditional software: their behavior is not fixed at deployment but continuously shaped by experience, feedback, and context. Applying operational principles inherited from DevOps or MLOps, built for deterministic software and traditional ML systems, assumes that system behavior can be managed through versioning, monitoring, and rollback. This assumption breaks down for Agentic AI systems whose learning trajectories diverge over time. This introduces non-determinism making system reliability a challenge at runtime. We argue that architecting such systems requires a shift from managing control loops to enabling dynamic co-evolution among agents, infrastructure, and human oversight. To guide this shift, we introduce CHANGE, a conceptual framework comprising six capabilities for operationalizing Agentic AI systems: Contextualize, Harmonize, Anticipate, Negotiate, Generate, and Evolve. CHANGE provides a foundation for architecting an AgentOps platform to manage the lifecycle of evolving Agentic AI systems, illustrated through a customer-support system scenario. In doing so, CHANGE redefines software architecture for an era where adaptation to uncertainty and continuous evolution are inherent properties of the system.

Problem

• Agentic AI
• non-determinism
• AgentOps
• system reliability
• continuous evolution

Innovation

• Agentic AI
• AgentOps
• CHANGE framework
• dynamic co-evolution
• non-deterministic systems