IASCI Research Publishing
Secure Networks and Systems Computing
Research Article Published October 9, 2026 Article snsc20260005

Constraint-Aware Infrastructure Script Generation with Multi-Agent Verification

Read & download PDF
Abstract

Infrastructure-as-code scripts are now widely used to manage cloud deployment, but automatically generated configuration files often contain incorrect resource dependencies, unsafe permission settings, invalid network rules, and excessive resource allocation. This study examines infrastructure script generation under deployment, security, and cost constraints. We propose DeployAgent, a multi-agent model that coordinates a requirement interpretation agent, a cloud resource planning agent, a configuration generation agent, a policy verification agent, and a cost-tuning agent. The requirement interpretation agent extracts service topology, workload scale, storage demand, access rules, and availability targets from natural-language deployment requests. The resource planning agent selects cloud components such as containers, load balancers, databases, storage buckets, and virtual networks. The configuration generation agent produces Terraform, Kubernetes YAML, and Helm configuration files. The policy verification agent checks dependency order, namespace isolation, secret exposure, least-privilege access, and network reachability. The cost-tuning agent adjusts instance size, replica count, autoscaling thresholds, and storage classes. The evaluation used deployment records from three cloud-native software projects over a six-month period. These records included 312 real deployment tickets, 1,870 historical configuration files, 46 service dependency graphs, and runtime logs from 11 Kubernetes clusters. In the replay experiment, DeployAgent successfully generated deployable configurations for 81.4% of tickets, while the single-agent model achieved 63.7%. Manual review found that unsafe permission assignments were reduced from 22.6 cases per 100 scripts to 7.9 cases, and invalid dependency definitions were reduced by 48.3%. In a staged deployment environment, the rollback rate decreased from 18.2% to 6.5%. Resource tuning also reduced average monthly cloud cost estimates by 14.7% without violating CPU, memory, or availability requirements. These findings show that multi-agent verification can improve the reliability, security, and economic efficiency of generated infrastructure code.

Keywords
Infrastructure as codecloud deploymentconfiguration generationpolicy verificationKubernetesTerraformmulti-agent systems
References
  1. Zhang, Z. (2026). A Study on the Impact of Cost Presentation on Decision-making Bias and Cancellation Behavior in Online Subscriptions. Available at SSRN 7349839.
  2. Mini Han Wang , " AI-Powered Innovations in Ophthalmic Diagnosis and Treatment ", Bentham Science Publishers (2025). https://doi.org/10.2174/97988988122871250101.
  3. Qi, C., & Qiao, X. (2026). Building and Operating a Large Scale Multi-Agent System: A Case Study from Industry. Available at SSRN 6795198.
  4. Hong, Z., Liang, S., Xu, T., & Chen, H. (2026). A Study on Failover Verification and Recovery Objective Prediction for Cross-Region Cloud Services.
  5. Quan, Q., Gao, Y., & Wang, Q. (2025). The impact of teacher emotional support on students' engagement in AI-mediated English learning environments: The mediating role of resilience and self-efficacy. Acta Psychologica, 260, 105766.
  6. Zhang, Z., Wang, J., Li, Z., Wang, Y., & Zheng, J. (2025). Anncoder: A mti-agent-based code generation and optimization model. Symmetry, 17(7), 1087.
  7. Wu, J., Zhang, J., Wu, D., & Peng, Y. (2026). Visual Transformation Mechanisms for Integrating Digital Cultural Heritage Resources into Junior High School Art Curricula.
  8. Huang, J., Xu, T., Yin, J., & Yang, J. (2026). Data Quality Monitoring and Intelligent Scheduling Optimization in Financial Data Workflow Automation. Available at SSRN 7179338.
  9. Xu, Y., Cui, J., Zhu, Z., Shang, H., Luan, S., Xu, M., ... & Zhu, S. (2026). Wam-flow: Parallel coarse-to-fine motion planning via discrete flow matching for autonomous driving. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 24918-24928).
  10. Zheng, J., & Makar, M. (2022). Causally motivated multi-shortcut identification and removal. Advances in Neural Information Processing Systems, 35, 12800-12812.
  11. Xu, T., Zhu, W., & Zhang, J. (2026). A Study on the Application of Alternative Data in Credit Assessment for the Unbanked Population.
  12. Xiong, W., Guo, Y., & Zeng, Y. (2026). A Study on the Energy Efficiency of MEP Systems and Coordinated Dispatch Mechanisms for Multi-energy Systems in High-density Urban Buildings. Available at SSRN 7120518.
  13. Zheng, X., Chen, X., Gong, S., Griffin, X., & Slabaugh, G. (2025, September). Xfmamba: Cross-fusion mamba for multi-view medical image classification. In International Conference on Medical Image Computing and Computer-Assisted Intervention (pp. 672-682). Cham: Springer Nature Switzerland.
  14. Zhao, J., Fan, J., & Li, L. (2026). A Study on an Explainable Causal-Enhanced LLM Agent for Predicting the Forming Quality of Automotive Component Materials.
  15. You, S. (2026). Verifiable Audit Mechanisms in AI Compliance Automation: Scalability. Available at SSRN 6547458.
  16. Jiao, Y., Shi, T., Zhao, B., & Wang, A. (2026). The Impact of VR Sketching Simulations on the Assessment of Scale and Site Suitability in Public Art Spaces.
  17. Su, J., He, C., Zhu, F., Xu, X., Guan, D., & Si, C. (2024, September). Hpff: Hierarchical locally supervised learning with patch feature fusion. In European Conference on Computer Vision (pp. 293-309). Cham: Springer Nature Switzerland.
  18. Liang, S., Du, Y., Chen, W., & Liu, Z. (2026). Order Allocation and Emergency Transportation Decisions Amid Multi-Source Procurement Disruptions.
  19. Bao, Y., & Wang, H. (2026). Orion: A High-Throughput, Fault-Tolerant Event Routing Architecture for Hyperscale Data Streams. Fault-Tolerant Event Routing Architecture for Hyperscale Data Streams (January 01, 2026).
  20. Yang, Q., & Du, Y. (2026). Predicting Rollback Risks and Controlling Gradual Rollout Traffic for Online Ranking Feature Deployments.
  21. Lyu, Y., Liu, K., Cao, Z., Luo, Y., Yin, L., Yang, T., & Chen, Z. (2026). FLAIR: An LLM-integrated multi-layer framework for fine-grained activity type inference in human trajectory data. Transportation Research Part C: Emerging Technologies, 190, 105787.
  22. Zhao, Z., & Welsch, R. E. (2026). Point-in-Time Financial RAG with Frozen LLMs and Market-Feedback Adaptive Retrieval. arXiv preprint arXiv:2605.31201.
  23. Yuan, Y., Huang, J., Yin, J., & Xu, T. (2026). Confidence Calibration and Semantic Error Analysis for Ambiguous Coreference Resolution in User-generated Social Media Text. Available at SSRN 7393238.
  24. Huang, Q., Xu, Z., Zhang, X., & Zhang, J. (2025). UniShield: An Adaptive Multi-Agent Framework for Unified Forgery Image Detection and Localization. arXiv preprint arXiv:2510.03161.
  25. Liang, J., Xiao, Y., Yang, H., Yu, Z., Liu, J. N., & Yang, K. (2026, April). C-HyPOD: Causal Hyperbolic Representation Learning with Prototype Orthogonal Disentanglement for Graph Out-of-Distribution Recommendation. In Proceedings of the ACM Web Conference 2026 (pp. 6541-6550).
  26. Xi, X., Chen, P., Qiu, Y., Luo, R., Tong, P., & Liang, J. Video-BCI: Bayesian Cognitive Integration of Self-Prior Hypotheses for Video Understanding. In Forty-third International Conference on Machine Learning.
  27. Liang, S., Hsu, K. H., & Liu, Z. (2026). Rolling Scheduling and Capacity Balancing for Server Assembly Under Engineering Change Disturbances.
  28. Xu, Z., Zhang, X., Li, R., Tang, Z., Huang, Q., & Zhang, J. (2024). Fakeshield: Explainable image forgery detection and localization via multi-modal large language models. arXiv preprint arXiv:2410.02761.
  29. Chaoyong Ma, Nan Si, Xuewei Song, Chen Liang and Haoming Luo, A Bearing Fault Diagnosis Method Based on Concise Empirical Wavelet Transform, International Journal of Comprehensive Engineering，2023, 12(1), 1-6
  30. Bing Wang, Haihong Tang, Xiaojia Zu and Wuwei Feng, Application of Parameter Adaptive VMD in Bearing Fault Diagnosis, International Journal of Comprehensive Engineering，2023, 12(1), 34-42
  31. Bao, Y., Qiu, Y., & Wang, H. (2026). FLARE: A Real-Time Framework for Detecting Malicious Account Activities at Internet Scale. Available at SSRN 7185659.
  32. Xu, Z., Zhang, X., Zhou, X., & Zhang, J. (2025). AvatarShield: Visual Reinforcement Learning for Human-Centric Video Forgery Detection. arXiv preprint arXiv:2505.15173.
  33. Yuan, Y., Xu, T., Yin, J., & Huang, J. (2026). Modeling Loading Anomalies and Identifying Root Causes in Media Consumption Workflows on Large Social Media Platforms. Available at SSRN 7393318.
  34. Tian Teng and Xiao Zhang, Design Principles and Feasibility Assessment of an Intelligent Spare-Parts Shelving System for Shipboard Storage Environments, Journal of Comprehensive Engineering，2026, 15(1), 24-30
  35. Jiang, C. (2026). Information doesn’t work? Testing experiential drivers of VR application in heritage tourism by affective-cognitive pathways. Journal of Hospitality and Tourism Technology, 1-28.
  36. Jianheng Liang, Yang Yang, Ran Zhang, Guican Wu, Yuanyuan Yang, TaiFu Li, Honglin Duan and Yuyan Li, Research on Perfume User Experience Evaluation Based on Human Machine Hybrid Generation Adversarial Network, International Journal of Comprehensive Engineering，2024, 13(1), 40-54
  37. Xi Qiao, Di Zhao, Nan Si, Jifeng Sui and Yonggang Xu, Weighting Spectrum Editing Based on Amplitude Mapping and Its Application in Composite Fault Diagnosis of Rolling Bearings, International Journal of Comprehensive Engineering，2024, 13(1), 13-21
  38. Wang, T., & Xia, Z. (2025). Stability of In-Context Learning: A Spectral Coverage Perspective. arXiv preprint arXiv:2509.20677.
  39. Xixin Chen, Ming Tu, Lei Su and Ke Li, Rolling Bearing Fault Diagnosis Based on Digital Twin Method, International Journal of Comprehensive Engineering，2024, 13(1), 22-39
  40. Liu, T., He, J., Zhou, R., Song, J., Liu, H., & Liang, Y. (2025). Revolutionizing clinical decision making through deep learning and topic modeling for pathway optimization. Scientific Reports, 15(1), Article 28787. https://doi.org/10.1038/s41598-025-12679-z
  41. Wu, X., Xing, X., Yao, J., Qian, Q., & Song, J. (2025). Scnet: spectral convolutional networks for multivariate time series classification. Applied Intelligence, 55(6), Article 456. https://doi.org/10.1007/s10489-025-06352-1
  42. Ma, C., Song, J., Xu, Y., Fan, H., Wu, X., & Sun, T. (2024). Vehicle-Based Machine Vision Approaches in Intelligent Connected System. IEEE Transactions on Intelligent Transportation Systems, 25(3), 2827-2836. https://doi.org/10.1109/TITS.2023.3276325
Publication details
Journal
Secure Networks and Systems Computing
Volume
1 (2026)
Issue
1 · Forthcoming issue
Article number
snsc20260005
License
CC BY 4.0