In the cloud native environment, microservice architecture faces dual challenges of semantic ambiguity in service configuration and dependence on human experience for change generation. Traditional flow limiting and resource scheduling methods suffer from static nature, insufficient global optimization, and lack of collaboration. Research Method: We propose a microservice orchestration framework that uses Large Language Models (LLMs). It accurately parses natural language requirements and converts them into precise service configurations, achieving a 95.2% success rate in benchmarks, which utilizes LLM to parse service configuration semantic information to achieve accurate mapping from natural language to configuration parameters. Combined with reinforcement learning (such as DQN model), it dynamically generates flow limiting strategies and container resource adjustment schemes, supporting non interactive/interactive collaborative adjustment modes. Research results: Under Workload 1 and Workload 2 workloads, the request success rate is on average 57% higher than the static method and 32% -56% higher than the SPCB algorithm; In the scenario of dynamic changes in resources, the state space expansion (including the total amount and arrival rate of resources) is used to further reduce the response time violation rate and maximize the request success rate. Conclusion: This framework utilizes LLM semantic parsing and reinforcement learning strategies to generate advantages, achieving intelligent collaboration between microservice request connection limits and container resources, improving system stability and resource utilization, and providing a new path for cloud native microservice orchestration.

Yunshu Zhang. Research on LLM-Driven Intelligent Architecture Design and Autonomy Mechanism Construction for Cloud-Native Control Planes. International Journal of Multimedia Computing (2026), Vol. 7, Issue 1: 62-72. https://doi.org/10.38007/IJMC.2026.070108

[1] Huang X, Gu R, Huang Y. Towards Efficient Serverless MapReduce Computing on Cloud-Native Platforms[J]. Big Data Mining and Analytics, 2025, 8(3):575-591. DOI:10. 26599/BDMA. 2024. 9020084.

[2] Mahmud R, Jin J, Kua J, et al. Trusted Microservice Orchestration for Secure Edge Computing in Industrial Cyber-Physical Systems[J]. IEEE Network, 2025:1-1. DOI:10. 1109/mnet. 2025. 3541032.

[3] Q. Xu, "Implementation of Intelligent Chatbot Model for Social Media Based on the Combination of Retrieval and Generation, " 2025 2nd International Conference on Intelligent Algorithms for Computational Intelligence Systems (IACIS), Hassan, India, 2025, pp. 1-7, doi: 10. 1109/IACIS65746. 2025. 11210989.

[4] M. Zhang, "Research on Joint Optimization Algorithm for Image Enhancement and Denoising Based on the Combination of Deep Learning and Variational Models, " 2025 International Conference on Intelligent Communication Networks and Computational Techniques (ICICNCT), Bidar, India, 2025, pp. 1-5, doi: 10. 1109/ICICNCT66124. 2025. 11232800.

[5] Wu Y. Software Engineering Practice of Microservice Architecture in Full Stack Development: From Architecture Design to Performance Optimization[J]. 2025.

[6] Sun J. Quantile Regression Study on the Impact of Investor Sentiment on Financial Credit from the Perspective of Behavioral Finance[J]. 2025.

[7] Wang Y. Application of Data Completion and Full Lifecycle Cost Optimization Integrating Artificial Intelligence in Supply Chain[J]. 2025.

[8] Chen M. Research on Automated Risk Detection Methods in Machine Learning Integrating Privacy Computing[J]. 2025.

[9] Wu Y. Optimization of Generative AI Intelligent Interaction System Based on Adversarial Attack Defense and Content Controllable Generation[J]. 2025.

[10] Sun, Q. (2026). Research on a Robotic Natural Language Intelligent Decision-Making Framework Based on Large Language Models, Thinking Chain Reasoning, and Multi-Agent Collaboration.

[11] Wang, Y. (2026). Research on the Application of Artificial Intelligence in Supply Chain Risk Early Warning.

[12] Liu, H. (2026). Research on the Application of Causal Reasoning Method in Content Compliance Experimental Evaluation.

[13] Ding, J. (2025). Research On CODP Localization Decision Model Of Automotive Supply Chain Based On Delayed Manufacturing Strategy. arXiv preprint arXiv:2511. 05899.

[14] Yu, X. (2025). Digital Transformation Empowers Growth Marketing with Marketing Data Analysis Integration and Real-Time Display Strategy.

[15] Yin, J. (2026). Research on Financial Time Series Prediction and Multiscale Correlation Based on the Fusion of Network Big Data and Deep Learning.

[16] Hou, Y. (2026). Research on BIOS and BMC Compatibility Optimization Methods for Cross-Generation Servers in Production Environments.

[17] Han, X. (2026). Research on Process Decision-Making Behavior under Incomplete Information Conditions in Automobile Manufacturing Systems.

[18] Chang, Chen-Wei. "Compiling Declarative Privacy Policies into Runtime Enforcement for Cloud and Web Infrastructure. " (2025).

[19] Lu, Z. (2025). Design and Practice of AI Intelligent Mentor System for DevOps Education. European Journal of Education Science, 1(3), 25-31.

[20] Wu Y. Software Engineering Practice of Microservice Architecture in Full Stack Development: From Architecture Design to Performance Optimization[J]. 2025.

[21] Huijie Pan. Discussion on Low-Latency Computing Strategies in Real-Time Hardware Generation. International Journal of Neural Network (2025), Vol. 4, Issue 1: 57-64.

[22] Wu, W. (2025, June). Construction and optimization of intelligent gateway software management platform based on jenkins cluster management under cloud edge integration architecture in industrial internet of things. In International Conference on 6G Communications Networking and Signal Processing (pp. 633-645). Singapore: Springer Nature Singapore.

[23] Liu, X. , & Yang, D. (2025, March). LLM Data Strategy: Improving Data Availability and Efficiency. In Doctoral Symposium on Computational Intelligence (pp. 425-437). Singapore: Springer Nature Singapore.

[24] Zhang, C. , Han, J. , Zou, Y. , Dong, K. , Li, Y. , Ding, J. , & Han, X. (2024, April). Detecting the anomalies in LiDAR pointcloud. In WCX SAE World Congress Experience. SAE Technical Paper.

[25] Huang, J. (2025, September). Performance Evaluation Index System and Engineering Best Practice of Production-Level Time Series Machine Learning System. In 2025 International Conference on Intelligent Communication Networks and Computational Techniques (ICICNCT) (pp. 01-07). IEEE.