Jul 2026· European Conference on Artificial Intelligence· pp. 1-6· 1 citation· 20 references
Abstract
Managing modern cloud-native infrastructure is, frankly, a problem that has grown faster than our tools for handling it. Continuous delivery pipelines, ephemeral containers, and sprawling multi-cloud Infrastructure-as-Code (IaC) ecosystems create an operational surface that expands combinatorially with organisational scale and static rule-based monitoring simply cannot keep up. This paper presents InfraAgent, a five-agent agentic AI framework designed for predictive infrastructure management and autonomous deployment operations in heterogeneous multi-cloud settings. The framework brings together: a Temporal Graph Attention Network (T-GAN) agent that jointly models infrastructure dependency topology and multi-variate telemetry for deployment failure prediction across 1-hour, 6-hour, and 24-hour horizons; a Remediation Planning Agent (RPA) built on a Large Language Model (LLM) that generates context-aware IaC patches, rollout prescriptions, and rollback directives directly from risk scores; a Deployment Safety Agent (DSA) that enforces configurable pre-flight autonomy gates; a Capacity Forecasting Agent (CFA) built on a Temporal Fusion Transformer (TFT) for probabilistic 24-hour to 72-hour demand forecasting; and a Continuous Operational Intelligence Orchestrator (COIO) that provides closed-loop governance, cryptographic auditability, and online model adaptation. We evaluate InfraAgent on 47,800 deployment events and 310,000 telemetry snapshots drawn from AWS, Azure, and GCP production environments. The results show a Mean Time to Detection of 4.3 minutes (an 85.2% reduction over rule-based baselines), a deployment failure prediction F1 of 0.931, a 76.8% reduction in production incidents per 100 Continuous Integration/Continuous Delivery (CI/CD) runs, and 91.4% capacity forecast accuracy at the 72-hour horizon, suggesting that coordinated agentic reasoning grounded in graph-temporal learning can meaningfully shift cloud operations from reactive firefighting toward continuous, self-correcting infrastructure assurance.
Multi-cloud adoption enables resilience, flexibility and vendor independence, but it also increases operational
complexity through heterogeneous interfaces, fragmented moni-toring, inconsistent governance, and difficult incident response.
Traditional DevOps and AIOps solutions provide monitoring, automation or optimisation in isolation, but they rarely deliver
end-to-end autonomous, governed and explainable multi-cloud infrastructure operations. This paper proposes AutoInfraOps,
an agentic DevOps coordinator for autonomous multi-cloud monitoring, optimisation, governance and self-healing infrastructure operations. The framework integrates specialised agents for monitoring, diagnosis, planning, optimisation, governance
and remediation. It uses a multi-cloud adapter layer for AWS, Azure and GCP, an event-driven runtime for agent coordina-tion,
anomaly detection for SLA violation identification, cost-performance scoring for workload placement, Human-in-the-Loop
approval for high-risk actions, and SHA-256 hash-chain audit logging for decision traceability. The system is evaluated using
simulated scenarios including AWS latency spike, Azure cost anomaly, GCP availability drop, cross-cloud dependency failure,
cascading failure, high-risk failover and rollback events. Experimental results indicate reduced incident response time, improved
SLA compliance, cost-aware remediation, and stronger governance visibility. AutoInfraOps demonstrates a practical foundation
for autonomous, explainable and policy-aware multi-cloud operations.
B. Reddy, D. D. Prasad· International Journal for Re...· 0 citations
Traditional cloud monitoring often relies on static remediation procedures that are difficult to adapt to dynamic and heterogeneous infrastructures. This paper proposes an agentic LLM-based architecture for adaptive remediation planning from confirmed cloud anomalies. The goal is not to replace anomaly detectors, but to transform confirmed anomaly events into structured, policy-constrained remediation artifacts suitable for human-supervised operational workflows.The proposed workflow combines anomaly intake, contextual validation, playbook retrieval, and constrained playbook generation through a message-driven Multi-Agent System. Retrieval-Augmented Generation is used to correlate current incidents with historical knowledge and existing procedures, while deterministic guardrails enforce schema validation, policy constraints, command allow/deny lists, critical-resource checks, and human approval for high-impact or previously unseen actions.A containerised Proof of Concept demonstrates that confirmed anomalies can be transformed into CACAO-compatible remediation drafts within operationally reasonable time bounds. The evaluation focuses on generating and validating remediation plans under explicit operational constraints, rather than on anomaly detection benchmarking or on production-scale autonomous execution.
Paolo Palmiero, A. Iannaccone, D. Granata et al.· International Conference on...· 0 citations
Experimental results show that the proposed self-calibrating agentic framework successfully profiles the zero-knowledge workloads, achieving a higher accuracy than baseline LLM agents and establishing a robust foundation for deploying autonomous AI in decentralized infrastructures.
Fin Gentzen, Marla Grunewald, Iulisloi Zacarias et al.· 0 citations
Static continuous integration and continuous delivery pipelines remain difficult to adapt when repositories,
dependencies, deployment targets, and operational conditions change. Manual configuration also slows failure diagnosis and
prevents pipelines from learning from previous executions. This paper presents DevOps-Pilot, a closed-loop agentic AI
framework for intelligent DevOps automation. The framework analyses repository context, detects languages, dependency files,
build tools, test frameworks, Docker assets, and Kubernetes manifests, and then uses LLM-assisted planning to generate Jenkinscompatible pipeline definitions. Pipeline execution is monitored through a Flask dashboard and SQLite-backed history store,
while anomaly detection and self-healing logic recommend recovery actions for installation, testing, and deployment failures. A
reinforcement learning-inspired optimisation policy updates cache, parallel testing, retry, and timeout settings from observed
rewards. The academic prototype was evaluated in simulation mode across four repositories and nine pipeline runs. Results show
six successful and three failed runs, a success rate of 66.67%, an average execution time of 120.52 seconds, and an average
reward of 3.2641. The findings indicate the feasibility of closed-loop CI/CD automation for adaptive software delivery.
A. Reddy, A. Jitendra· International Journal for Re...· 0 citations
Enterprises increasingly distribute computing workloads across multiple public and private cloud providers to reduce cost, avoid vendor lock-in, and improve resilience, but this multiplies the complexity of deciding, for every incoming task, which provider to use. Static or single-objective heuristics — always choosing the cheapest or always the fastest provider — routinely fail because cost, latency, and reliability trade off against one another in ways that shift with demand and provider conditions. This paper proposes and evaluates an explainable agentic AI framework for multi-cloud task allocation built on a contextual-bandit agent (LinUCB) that observes each provider's current price, estimated latency, and load before autonomously selecting a placement, then updates its policy online from the resulting cost, latency, and service-level-agreement (SLA) outcome. Because no public multi-cloud trace exposes simultaneous, ground-truth price/latency/capacity data across providers, the framework is evaluated on a controlled, fully documented discrete-time simulation of four heterogeneous providers under realistic load dynamics — a standard and disclosed methodology in this research area. Across 30 independent simulation runs of 3,000 tasks each, the agent achieved a statistically significant improvement over the strongest single fixedweight heuristic baseline (Static-Weighted) on every safety- and balance-related metric: 86.2% fewer SLA violations, 20.9% lower average latency, and 19.6% higher load-balancing fairness (Jain's index = 0.955 vs. 0.799, paired t-test, all p < 0.001), at a 20.6% higher cost. Under a simulated transient provider degradation (a 5× latency spike on one provider for 20% of a run), the agent held SLA violations to 0.4%, versus 9.9% for naive round-robin routing and 40.2% for cost-only routing, while remaining markedly cheaper than a purely latencyreactive baseline. To support the "explainable" requirement of agentic systems intended for production use, the framework exposes two complementary explanation layers: the bandit's own per-provider linear coefficients, and a surrogate Random Forest trained to imitate the agent's decisions (99.6% fidelity), whose permutation importance identifies observed latency and price as the dominant drivers of every allocation decision. These results indicate that a lightweight, interpretable contextual-bandit agent can deliver a favourable, auditable balance of cost, latency, SLA compliance, and fairness in multi-cloud environments, including under operational stress, without the opacity of deeper reinforcement learning or black-box agentic architectures.
Dr. Sajitha A V· International Journal of Int...· 0 citations
This work introduces Model Automated Deployment Engine (MADE), a dual-agent coordination system that iteratively constructs and validates the deployment artifacts, updates its deployment belief based on execution feedback, and revisits invalid upstream artifacts until the model is successfully served as a ready-to-call API that can then be used by other agents.
Yicheng Liu, Bolin Zhang, Weiran Liu et al.· 0 citations