Automated Cloud Infrastructure-as-Code Reconciliation with AI Agents

• URL: http://arxiv.org/abs/2510.20211v1
• Date: Thu, 23 Oct 2025 04:57:00 GMT
• Title: Automated Cloud Infrastructure-as-Code Reconciliation with AI Agents
• Abstract summary: NSync is an automated system for IaC reconciliation that propagates out-of-band changes back into the IaC program.<n>NSync gleans insights from API traces to detect drift (i.e., non-IaC changes) and reconcile it.
• Score: 8.4355888644149
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Cloud infrastructure is managed through a mix of interfaces -- traditionally, cloud consoles, command-line interfaces (CLI), and SDKs are the tools of choice. Recently, Infrastructure-as-Code/IaC frameworks (e.g., Terraform) have quickly gained popularity. Unlike conventional tools, IaC~frameworks encode the infrastructure in a "source-of-truth" configuration. They are capable of automatically carrying out modifications to the cloud -- deploying, updating, or destroying resources -- to bring the actual infrastructure into alignment with the IaC configuration. However, when IaC is used alongside consoles, CLIs, or SDKs, it loses visibility into external changes, causing infrastructure drift, where the configuration becomes outdated, and later IaC operations may undo valid updates or trigger errors. We present NSync, an automated system for IaC reconciliation that propagates out-of-band changes back into the IaC program. Our key insight is that infrastructure changes eventually all occur via cloud API invocations -- the lowest layer for cloud management operations. NSync gleans insights from API traces to detect drift (i.e., non-IaC changes) and reconcile it (i.e., update the IaC configuration to capture the changes). It employs an agentic architecture that leverages LLMs to infer high-level intents from noisy API sequences, synthesize targeted IaC updates using specialized tools, and continually improve through a self-evolving knowledge base of past reconciliations. We further introduce a novel evaluation pipeline for injecting realistic drifts into cloud infrastructure and assessing reconciliation performance. Experiments across five real-world Terraform projects and 372 drift scenarios show that NSync outperforms the baseline both in terms of accuracy (from 0.71 to 0.97 pass@3) and token efficiency (1.47$\times$ improvement).

Related papers

• From Architecture to Binary: Ensuring Cross-Domain Consistency in Model-Based Airborne Software Development [0.8749675983608171]
  This paper presents an airborne software development approach for manned and unmanned aerial vehicles.<n>It aims to reduce inconsistencies across system, model-based functional, and embedded software domains.
  arXiv  Detail & Related papers  (2026-08-28T10:16:36Z)
• IACM-RL: Intent-Aware Context Management and Reinforcement Learning for Complex Tool Invocation under Dynamic Intent Fluctuations [86.93902234336393]
  IACM-RL is a comprehensive framework for robust tool invocation.<n>We introduce the DynamicIntent pipeline, synthesizing trajectories across 13 fine-grained fluctuation scenarios.<n>Second, IACM-RL deploys a BeliefState-based Self-Generated Context Manager.
  arXiv  Detail & Related papers  (2026-08-03T12:09:50Z)
• Design and Implementation of an Open-Source Security Framework for Cloud Infrastructure [0.0]
  This paper presents an open-source cloud-infrastructure security framework built with a microservice architecture.<n>The framework integrates four core services: identity and access control unification, configuration-baseline intelligent checking over assets, real-time threat monitoring, and automated remediation.<n>The project is released under Apache 2.0 to lower entry cost by about 40% for small and medium teams.
  arXiv  Detail & Related papers  (2026-04-03T03:50:11Z)
• Ambig-IaC: Multi-level Disambiguation for Interactive Cloud Infrastructure-as-Code Synthesis [8.743123758115608]
  Large Language models (LLMs) are increasingly being used to generate IaC configurations from natural language.<n>We observe that ambiguity in IaC exhibits a tractable compositional structure.<n>We propose a training-free, disagreement-driven framework that generates diverse candidate specifications.
  arXiv  Detail & Related papers  (2026-04-01T20:27:43Z)
• Dynamic analysis enhances issue resolution [53.50448142467294]
  DAIRA (Dynamic Analysis-enhanced Issue Resolution Agent) is an automated repair framework that embeds dynamic analysis into the agent's reasoning cycle.<n> Driven by a Test Tracing-Driven methodology, DAIRA utilizes lightweight monitors to extract critical runtime data.<n>When powered by Gemini 3 Flash Preview, DAIRA establishes a new state-of-the-art (SOTA) performance, achieving a 79.4% resolution rate on the SWE-bench Verified dataset.
  arXiv  Detail & Related papers  (2026-03-23T14:48:54Z)
• Cognitive Platform Engineering for Autonomous Cloud Operations [0.14658400971135652]
  This paper introduces Cognitive Platform Engineering, a next-generation paradigm that integrates sensing, reasoning, and autonomous action directly into the platform lifecycle.<n>A prototype implementation built with Terraform, Open Policy Agent, and ML-based anomaly detection demonstrates improvements in mean time to resolution, resource efficiency, and compliance.
  arXiv  Detail & Related papers  (2026-01-24T18:17:49Z)
• Accelerating Control Systems with GitOps: A Path to Automation and Reliability [0.0]
  Poster explores how GitOps enables fully automated, auditable, and version-controlled infrastructure management.<n>Fermilab's ACORN project aims to modernize control system infrastructure and software.
  arXiv  Detail & Related papers  (2025-11-07T19:04:05Z)
• Multi-IaC-Eval: Benchmarking Cloud Infrastructure as Code Across Multiple Formats [12.813627159588032]
  We present Multi-IaC-Bench, a novel benchmark dataset for evaluating Large Language Models (LLMs)-based IaC generation and mutation.<n>The dataset consists of triplets containing initial IaC templates, natural language modification requests, and corresponding updated templates.<n>We evaluate several state-of-the-art LLMs on Multi-IaC-Bench, demonstrating that while modern LLMs can achieve high success rates (>95%) in generating syntactically valid IaC across formats, significant challenges remain in semantic alignment and handling complex infrastructure patterns.
  arXiv  Detail & Related papers  (2025-08-21T22:37:18Z)
• Cloud Infrastructure Management in the Age of AI Agents [8.243598669679354]
  We make a case for developing AI agents powered by large language models (LLMs) to automate cloud infrastructure management tasks.<n>In a preliminary study, we investigate the potential for AI agents to use different cloud/user interfaces.<n>We report takeaways on their effectiveness on different management tasks, and identify research challenges and potential solutions.
  arXiv  Detail & Related papers  (2025-06-13T22:50:12Z)
• SacFL: Self-Adaptive Federated Continual Learning for Resource-Constrained End Devices [38.27552394580526]
  Dynamic nature of data, characterized by continuous changes or data drift, poses significant challenges for on-device machine learning models.<n>Traditional centralized approach to continual learning is unsuitable for end devices due to privacy and data volume concerns.<n>FCL emerges as a promising solution, preserving user data locally while enhancing models through collaborative updates.
  arXiv  Detail & Related papers  (2025-05-01T07:26:35Z)
• MSCN: Multi-view Structural Convolution Network for Domain-Invariant Point Cloud Recognition of Autonomous Vehicles [1.7616042687330637]
  Multi-view Structural Convolution Network (MSCN) is a novel architecture designed to achieve domain-invariant recognition.<n>MSCN consistently outperforms state-of-the-art point cloud classification methods across all domain change scenarios.
  arXiv  Detail & Related papers  (2025-01-27T18:25:35Z)
• Rendering-Oriented 3D Point Cloud Attribute Compression using Sparse Tensor-based Transformer [52.40992954884257]
  3D visualization techniques have fundamentally transformed how we interact with digital content.<n>Massive data size of point clouds presents significant challenges in data compression.<n>We propose an end-to-end deep learning framework that seamlessly integrates PCAC with differentiable rendering.
  arXiv  Detail & Related papers  (2024-11-12T16:12:51Z)
• Statically Inferring Usage Bounds for Infrastructure as Code [0.9886108751871757]
  Infrastructure as Code (IaC) has enabled cloud customers to have more agility in creating and modifying complex deployments of cloud-provisioned resources. We propose a tool for fine-grained static usage analysis that works by modeling the inter-resource interactions in an IaC deployment as a set of constraints.
  arXiv  Detail & Related papers  (2024-02-23T22:27:56Z)
• Continual Learning From a Stream of APIs [90.41825351073908]
  Continual learning (CL) aims to learn new tasks without forgetting previous tasks. Existing CL methods require a large amount of raw data, which is often unavailable due to copyright considerations and privacy risks. This paper considers two practical-yet-novel CL settings: data-efficient CL (DECL-APIs) and data-free CL (DFCL-APIs)
  arXiv  Detail & Related papers  (2023-08-31T11:16:00Z)
• AdaPoinTr: Diverse Point Cloud Completion with Adaptive Geometry-Aware Transformers [94.11915008006483]
  We present a new method that reformulates point cloud completion as a set-to-set translation problem. We design a new model, called PoinTr, which adopts a Transformer encoder-decoder architecture for point cloud completion. Our method attains 6.53 CD on PCN, 0.81 CD on ShapeNet-55 and 0.392 MMD on real-world KITTI.
  arXiv  Detail & Related papers  (2023-01-11T16:14:12Z)
• SOLIS -- The MLOps journey from data acquisition to actionable insights [62.997667081978825]
  In this paper we present a unified deployment pipeline and freedom-to-operate approach that supports all requirements while using basic cross-platform tensor framework and script language engines. This approach however does not supply the needed procedures and pipelines for the actual deployment of machine learning capabilities in real production grade systems.
  arXiv  Detail & Related papers  (2021-12-22T14:45:37Z)
• Towards Lifelong Learning of End-to-end ASR [81.15661413476221]
  Lifelong learning aims to enable a machine to sequentially learn new tasks from new datasets describing the changing real world without forgetting the previously learned knowledge. An overall relative reduction of 28.7% in WER was achieved compared to the fine-tuning baseline when sequentially learning on three very different benchmark corpora.
  arXiv  Detail & Related papers  (2021-04-04T13:48:53Z)
• LC-NAS: Latency Constrained Neural Architecture Search for Point Cloud Networks [73.78551758828294]
  LC-NAS is able to find state-of-the-art architectures for point cloud classification with minimal computational cost. We show how our searched architectures achieve any desired latency with a reasonably low drop in accuracy.
  arXiv  Detail & Related papers  (2020-08-24T10:30:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.