Automated Synthesis of Cloud Emulators

• URL: http://arxiv.org/abs/2608.23842v1
• Date: Mon, 24 Aug 2026 21:29:52 GMT
• Title: Automated Synthesis of Cloud Emulators
• Abstract summary: CloudEmu is an automated approach that constructs emulators based on cloud documentation via neurosymbolic code synthesis.<n>Our evaluation shows the effectiveness of CloudEmu on major cloud provider (AWS and GCP) services in both coverage and accuracy.
• Score: 7.149847642627702
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: DevOps programming (e.g., using CLI/API scripts or IaC frameworks) is key to cloud infrastructure management. Unlike traditional programming tasks, DevOps program testing needs provisioning and execution against actual cloud resources, which is often time-consuming, unsafe, and costly. Cloud emulators have gained popularity for easing DevOps program testing; they are generally API-level mocks that can execute DevOps programs in a local environment. Still, building these emulators remains challenging: developers must manually interpret extensive cloud documentation and handcraft logic for each service, API, and their interaction. This does not scale to the complexity of the cloud, which is further a moving target as the services and APIs evolve. CloudEmu is an automated approach that constructs emulators based on cloud documentation via neurosymbolic code synthesis. The key idea is to combine LLMs' general strengths in documentation understanding and code generation with cloud-specific symbolic abstractions that suppress hallucinations and enforce precision at scale, while using the real cloud as an oracle for automated testing, repair, and alignment. Our evaluation shows the effectiveness of CloudEmu on major cloud provider (AWS and GCP) services in both coverage and accuracy. CloudEmu outperforms the existing leading tool LocalStack, which was manually developed by a large team of engineers over a decade.

Related papers

• DevOps-Gym: Benchmarking AI Agents in Software DevOps Cycle [84.01703913780946]
  Handling the DevOps cycle in real-world software requires analyzing large-scale projects, understanding dynamic program behaviors, leveraging domain-specific tools, and making sequential decisions.<n>We introduce DevOps-Gym, the first end-to-end benchmark for evaluating AI agents across core DevOps tasks.
  arXiv  Detail & Related papers  (2026-01-27T18:43:46Z)
• ABC-Bench: Benchmarking Agentic Backend Coding in Real-World Development [72.4729759618632]
  We introduce ABC-Bench, a benchmark to evaluate agentic backend coding within a realistic, executable workflow.<n>We curated 224 practical tasks spanning 8 languages and 19 frameworks from open-source repositories.<n>Our evaluation reveals that even state-of-the-art models struggle to deliver reliable performance on these holistic tasks.
  arXiv  Detail & Related papers  (2026-01-16T08:23:52Z)
• EnvScaler: Scaling Tool-Interactive Environments for LLM Agent via Programmatic Synthesis [101.67583081810136]
  Large language models (LLMs) are expected to be trained to act as agents in various real-world environments.<n>This process relies on rich and varied tool-interaction sandboxes.<n>We propose EnvScaler, an automated framework for scalable tool-interaction environments.
  arXiv  Detail & Related papers  (2026-01-09T14:32:06Z)
• AGOCS -- Accurate Google Cloud Simulator Framework [0.0]
  The Accurate Google Cloud Simulator (AGOCS) is a novel high-fidelity Cloud workload simulator based on parsing real workload traces.<n>The framework is able to reveal very precise and detailed parameters of the executed jobs, tasks and nodes.
  arXiv  Detail & Related papers  (2025-09-30T11:40:04Z)
• RefComp: A Reference-guided Unified Framework for Unpaired Point Cloud Completion [53.28542050638217]
  The unpaired point cloud completion task aims to complete a partial point cloud by using models trained with no ground truth.<n>Existing unpaired point cloud completion methods are class-aware, i.e., a separate model is needed for each object class.<n>We propose a novel unpaired point cloud completion framework, namely the Reference-guided Completion (RefComp) framework.
  arXiv  Detail & Related papers  (2025-04-18T16:40:16Z)
• Object as a Service: Simplifying Cloud-Native Development through Serverless Object Abstraction [1.4610038284393168]
  We propose a new paradigm, known as Object as a Service (O) that encapsulates application data and functions into the cloud object abstraction.<n>O relieves developers from resource and data management burden while offering built-in optimization features.<n>We develop a platform named Oparaca that offers state abstraction for structured and unstructured data with consistency and fault-tolerant guarantees.
  arXiv  Detail & Related papers  (2024-08-09T06:55:00Z)
• CloudEval-YAML: A Practical Benchmark for Cloud Configuration Generation [9.320732264679238]
  We present CloudEval-YAML, a practical benchmark for cloud configuration generation. The dataset consists of hand-written problems with unit tests targeting practical scenarios. The dataset consists of 1011 problems that take more than 1200 human hours to complete.
  arXiv  Detail & Related papers  (2023-11-10T01:49:57Z)
• Exploring Security Practices in Infrastructure as Code: An Empirical Study [54.669404064111795]
  Cloud computing has become popular thanks to the widespread use of Infrastructure as Code (IaC) tools. scripting process does not automatically prevent practitioners from introducing misconfigurations, vulnerabilities, or privacy risks. Ensuring security relies on practitioners understanding and the adoption of explicit policies, guidelines, or best practices.
  arXiv  Detail & Related papers  (2023-08-07T23:43:32Z)
• CWD: A Machine Learning based Approach to Detect Unknown Cloud Workloads [3.523208537466129]
  We develop a machine learning based technique to characterize, profile and predict workloads running in the cloud environment. We also develop techniques to analyze the performance of the model in a standalone manner.
  arXiv  Detail & Related papers  (2022-11-28T19:41:56Z)
• Object as a Service (OaaS): Enabling Object Abstraction in Serverless Clouds [2.0575037267955305]
  We propose a new abstraction level atop the function abstraction, known as Object as a Service (O) programming. O encapsulates the application data and function into the object abstraction and relieves the developers from resource and data management burdens. It also unlocks opportunities for built-in optimization features, such as software reusability, data locality, and caching.
  arXiv  Detail & Related papers  (2022-06-10T21:31:22Z)
• Auto-Split: A General Framework of Collaborative Edge-Cloud AI [49.750972428032355]
  This paper describes the techniques and engineering practice behind Auto-Split, an edge-cloud collaborative prototype of Huawei Cloud. To the best of our knowledge, there is no existing industry product that provides the capability of Deep Neural Network (DNN) splitting.
  arXiv  Detail & Related papers  (2021-08-30T08:03:29Z)

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.