# Automated Cloud Infrastructure-as-Code Reconciliation with AI Agents

arXiv: https://arxiv.org/abs/2510.20211 · HTML: https://mlsanity.com/paper/2510.20211/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 72 references that are in the map.
- First posted on arXiv 23 Oct 2025.

## Builds on (most cited first, 16 of 16)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [OpenHands: An Open Platform for AI Software Developers as Generalist Agents](https://mlsanity.com/paper/2407.16741/) (2024)
- [Agentless: Demystifying LLM-based Software Engineering Agents](https://mlsanity.com/paper/2407.01489/) (2024)
- [CodeT: Code Generation with Generated Tests](https://mlsanity.com/paper/2207.10397/) (2022)
- [RepairAgent: An Autonomous, LLM-Based Agent for Program Repair](https://mlsanity.com/paper/2403.17134/) (2024)
- [Agent-R: Training Language Model Agents to Reflect via Iterative Self-Training](https://mlsanity.com/paper/2501.11425/) (2025)
- [TroVE: Inducing Verifiable and Efficient Toolboxes for Solving Programmatic Tasks](https://mlsanity.com/paper/2401.12869/) (2024)
- [RepairLLaMA: Efficient Representations and Fine-Tuned Adapters for Program Repair](https://mlsanity.com/paper/2312.15698/) (2023)
- [AIOpsLab: A Holistic Framework to Evaluate AI Agents for Enabling Autonomous Clouds](https://mlsanity.com/paper/2501.06706/) (2025)
- [A Survey of LLM-based Automated Program Repair: Taxonomies, Design Paradigms, and Applications](https://mlsanity.com/paper/2506.23749/) (2025)
- [Towards Effectively Leveraging Execution Traces for Program Repair with Code LLMs](https://mlsanity.com/paper/2505.04441/) (2025)
- [Cloud Infrastructure Management in the Age of AI Agents](https://mlsanity.com/paper/2506.12270/) (2025)

## Built on by (most cited first, 5 of 5)

- [RIVA: Leveraging LLM Agents for Reliable Configuration Drift Detection](https://mlsanity.com/paper/2603.02345/) (2026)
- [Interactive Clarification for Cloud Infrastructure-as-Code Synthesis](https://mlsanity.com/paper/2604.02382/) (2026)
- [TerraRepair: A Tool-Grounded LLM Agent for Infrastructure-as-Code Repair](https://mlsanity.com/paper/2607.11390/) (2026)
- [Towards a Systems Foundation for Agentic Cloud Management](https://mlsanity.com/paper/2607.25883/) (2026)
- [Automated Synthesis of Cloud Emulators](https://mlsanity.com/paper/2608.23842/) (2026)

## Abstract (arXiv)

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× improvement).