The Agent Operating System (AOS), a vendor-neutral reference operating architecture for distributed agentic systems, is proposed as the operating architecture through which heterogeneous components can be composed into governable, reliable, observable, and interoperable agentic systems.
Abstract
Large language models have transformed artificial intelligence from isolated prediction services into components of long-running, distributed systems that reason, invoke tools, retrieve external state, delegate tasks, and act on behalf of users and organizations. The surrounding ecosystem has responded with agent frameworks, workflow engines, model-serving platforms, memory systems, communication protocols, and observability tools. These technologies improve execution, but they do not provide a stable, implementation-independent operating architecture for governing intent, selecting capabilities, preserving authority across delegation, controlling uncertainty, coordinating runtime behavior, and reconstructing why consequential actions occurred. This paper proposes the Agent Operating System (AOS), a vendor-neutral reference operating architecture for distributed agentic systems. AOS contains two internal planes: a Control&Governance Plane responsible for intent, policy, trust, authority, confidence, auditability, observability, and human oversight; and a Runtime&Coordination Plane responsible for agent lifecycle, workflow coordination, model and tool routing, context and memory coordination, scheduling, traffic management, and runtime assurance. Platform services, Linux or Windows, container runtimes, and physical infrastructure remain outside the AOS boundary and are integrated through explicit interfaces. The paper specifies AOS concepts, invariants, interface objects, optimization objectives, deployment profiles, and reliability responsibilities. It also identifies tradeoffs and unresolved research questions. AOS is not presented as a replacement for existing frameworks or infrastructure; it is proposed as the operating architecture through which heterogeneous components can be composed into governable, reliable, observable, and interoperable agentic systems.
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.
This work introduces the concept of an agentic transaction and proposes an ACID-compliant agent system framework that reinterprets the classical ACID properties for agent execution through four semantic guarantees: Semantic Atomicity, Semantic Consistency, Semantic Isolation, and Semantic Durability.
The emergence of agentic artificial intelligence is transforming the foundations of modern software architecture. Traditional distributed systems were designed around deterministic execution models in which predefined workflows and explicit logic governed system behavior. Agentic AI introduces a fundamentally different paradigm by enabling autonomous entities capable of adaptive decision-making, goal-oriented behavior, and contextual reasoning. While this shift increases flexibility and operational intelligence, it also introduces new forms of uncertainty. Autonomous agents operating simultaneously within distributed environments may produce divergent behaviors, make decisions based on incomplete information, and generate system states that are difficult to predict or control. These characteristics challenge traditional assumptions regarding reliability, coordination, and governance in enterprise systems. This paper introduces the concept of Contract-Bound Autonomy, a new architectural model for balancing autonomy and control in distributed agentic systems. Rather than constraining agents through rigid workflows, the proposed model defines explicit operational boundaries through contracts that specify permissible actions, risk limits, compliance constraints, and expected outcomes. Within these boundaries, agents retain the flexibility to adapt their behavior dynamically. The study develops a conceptual framework for understanding how distributed software systems can integrate autonomous agents while maintaining reliability, observability, and governance. It further examines the implications of contract-driven coordination, runtime enforcement, and boundary-aware decision-making in large-scale architectures. By reframing control as the management of acceptable behavioral space rather than deterministic instruction, this work contributes to the emerging field of agentic software systems and proposes a scalable foundation for trustworthy autonomous computing.
Ilker Kanatli· International Journal of Res...· 0 citations
Enterprise AI deployment is a coordination problem across business units, application and AI teams, testing, platform engineering, infrastructure, security, operations, and data governance. Use-case benchmarks show whether one agent completes one task, but not how changing capabilities, models, runtime mechanisms, capacity, and enterprise data should be owned, changed, admitted, or evidenced together. We present four responsibility objects as shared organizational contracts: Skill (reusable, versioned capability and workflow asset), Harness (runtime compiler and governor), Scaffold (execution/control boundary and NFR owner), and a stack-external data substrate under independent CIO-governed semantics and telemetry. The runtime core is A =, with the data substrate outside that stack. The central contribution is one bounded, falsifiable hypothesis, P1 (cost-aware capability-capacity separability): within a declared operating region, changing activated capability preserves the capacity-response interaction within a preregistered equivalence margin, while changing compatible Scaffold capacity preserves capability semantics up to a non-inferiority margin, and the required controls stay within a declared enforcement budget. Six design conditions become measured obligations whose coverage, violations, uncertainty, cost, and exclusions determine whether P1 is decidable. We propose a cluster-period randomized crossover experiment (balanced order, reset/washout, repeated seeds and failure regimes, cluster-aware uncertainty) with a four-state verdict: supported, falsified, conditional-engineering, or inconclusive. This paper contributes a contract-bounded runtime architecture, a source-preserving data substrate, and a falsifiable measurement protocol. It reports no completed implementation, experiment, dataset, or measured result.
Ya-Xiao Liu, Peng Liu, Yi-Wen Liu et al.· 0 citations
A unified, taxonomy-driven, and deployment-oriented survey of agentic AI systems, synthesizing recent advances through a modular reference architecture and a four-dimensional taxonomy that characterizes agents along the axes of autonomy, tool use, collaboration, and safety–governance is presented.
Sparsh Bajoria, Shreyanshu Ranjan, Adhitya M et al.· Cognitive Computation· 0 citations
Agentao is presented, a governed local-first runtime for tool-using LLM agents that separates model-generated action proposals from host-authorized execution through a layered architecture consisting of host-facing surfaces, a host contract, a runtime core, a permission-mediated tool system, and supporting subsystems for memory, replay, plugins, skills, sub-agents, and protocol integration.