Orchestrating LLMs and SLMs for Autonomous Enterprise Service Automation
Keywords:
Autonomous Enterprise Agents, Decision Automation Systems, IT Service Management Automation, Human Resources Service Delivery, Customer Service And Support Platforms, Agent-Based Orchestration, Self-Governing Software Agents, Cross-Domain Decision Workflows, Standardized Data Models, Enterprise Process Automation, Orchestration Layer Design, Scalability And Risk Management, Task Decomposition Frameworks, Collaborative Agent Systems, Third-Party Capability Extensions, Service Catalog Operations, Ticket Lifecycle Management, Incident Resolution Automation, Privacy And Confidentiality Requirements, Enterprise Data Protection.Abstract
Autonomous enterprise agents designed for orchestrated decision automation across information technology service management (ITSM), human resources service delivery (HRSD), and customer service and support (CSS) platforms are detailed. Growing enterprise demand for automation and decision support hinges on self-governing software agents capable of independent task scheduling and execution, yet ITSM, HRSD, and CSS environments present complex governance requirements that hinder the deployment of agent-based systems. Empirical evidence points to the existence of a shared set of conditions—standardized data models and commonplace processes, together with solutions supporting rudimentary automation—beneath the apparent diversity of cross-domain decision workflows. An agent composition is described, with an orchestration layer addressing scalability and risk management.
The software agents underpinning enterprise automation seek to relieve staff of routine, low-level decisions while delivering consistent, reliable results. Orchestrated instances feature additional layers facilitating expansive collaboration through the decomposition of complex tasks into multiple subtasks and the admission of new capabilities via third-party extensions. Two intertwining sets of requirements reflect the diversity of enterprise domains: the specific conditions imposed by service management platforms—issues governing service-catalog operations, ticket lifecycles, and incident-resolution processes—and wider concerns of privacy, confidentiality, and data protection, which are paramount when handling employee information.
References
1. Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J. D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., Agarwal, S., Herbert-Voss, A., Krueger, G., Henighan, T., Child, R., Ramesh, A., Ziegler, D. M., Wu, J., Winter, C., ... Amodei, D. (2021). Language models are few-shot learners. Advances in Neural Information Processing Systems, 33, 1877–1901.
2. Wei, J., Wang, X., Schuurmans, D., Bosma, M., Ichter, B., Xia, F., Chi, E., Le, Q. V., & Zhou, D. (2022). Chain-of-thought prompting elicits reasoning in large language models. Advances in Neural Information Processing Systems, 35, 24824–24837.
3. Pamisetty, A., Paleti, S., Adusupalli, B., Singireddy, J., Inala, R., & Nagabhyru, K. C. (2025). Explainable AI Systems for Credit Scoring and Loan Risk Assessment in Digital Banking Platforms. In 2025 IEEE 13th International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications (IDAACS) (pp. 1478–1483). IEEE. 2025 IEEE 13th International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications (IDAACS). https://doi.org/10.1109/idaacs68557.2025.11322144
4. Yao, S., Zhao, J., Yu, D., Du, N., Shafran, I., Narasimhan, K., & Cao, Y. (2023). ReAct: Synergizing reasoning and acting in language models. International Conference on Learning Representations.
5. Schick, T., Dwivedi-Yu, J., Dessì, R., Raileanu, R., Lomeli, M., Zettlemoyer, L., Cancedda, N., & Scialom, T. (2023). Toolformer: Language models can teach themselves to use tools. Advances in Neural Information Processing Systems, 36.
6. Chary, D. V., Meda, R., C, J. S. Mary., Narasimhachari, J. P., & A S, Y. (2025). TriFusionFormer: Tri-Modal Fusion Transformer Using Gated Modality Control and Multi-Scale Attention for Emotion Recognition. In 2025 International Conference on Communication, Computer, and Information Technology (IC3IT) (pp. 1–8). IEEE. 2025 International Conference on Communication, Computer, and Information Technology (IC3IT). https://doi.org/10.1109/ic3it66137.2025.11341646
7. Mialon, G., Dessì, R., Lomeli, M., Nalmpantis, C., Pasunuru, R., Raileanu, R., Rozière, B., Schick, T., Dwivedi-Yu, J., Simões, C., de Almeida, M. B., & Scialom, T. (2023). Augmented language models: A survey. Transactions of the Association for Computational Linguistics, 11, 31–49
8. Alshar, M. M., Shahdadpuri, N., Rajeshwari, M., Gupta, M., Joshi, N. R., & Singireddy, J. (2025). Enhanced Management & Performance of Remote Workforce with Cloud and AI-Driven HR Analytics. In 2025 3rd International Conference on Advances in Computation, Communication and Information Technology (ICAICCIT) (pp. 631–636). IEEE. 2025 3rd International Conference on Advances in Computation, Communication and Information Technology (ICAICCIT). https://doi.org/10.1109/icaiccit68829.2025.11434104
9. Muthusamy, V., Rizk, Y., Kate, K., Venkateswaran, P., Isahagian, V., Gulati, A., & Dube, P. (2023). Towards large language model-based personal agents in the enterprise: Current trends and open problems. Findings of the Association for Computational Linguistics: EMNLP 2023, 6909–6921.
10. Li, X., Wang, S., Zeng, S., Wu, Y., Tang, Y., Wang, Y., & Yang, Y. (2024). A survey on LLM-based multi-agent systems: Workflow, infrastructure, and challenges. Journal of Artificial Intelligence Research, 80, 1–50.
11. Krishnan, M., Nandan, B. P., Rongali, S. K., Meda, R., Kalisetty, S., & Singireddy, J. (2026, June). AI-Driven Data Engineering and Predictive Analytics Framework for Semiconductor Supply Chain Optimization and Digital Infrastructure Modernization. In 2026 6th International Conference on Intelligent Technologies (CONIT) (pp. 1-6). IEEE.
12. Wang, L., Ma, C., Feng, X., Zhang, Z., Yang, H., Zhang, J., Chen, Z., Tang, J., Chen, X., Lin, Y., Zhao, W. X., Wei, Z., & Wen, J. (2024). A survey on large language model based autonomous agents. Frontiers of Computer Science, 18, Article 186345.
13. Wang, F., Zhang, Z., Zhang, X., Wu, Z., Mo, T., Lu, Q., Wang, W., Li, R., Xu, J., Tang, X., He, Q., Ma, Y., Huang, M., & Wang, S. (2025). A comprehensive survey of small language models in the era of large language models: Techniques, enhancements, applications, collaboration with LLMs, and trustworthiness. ACM Transactions on Intelligent Systems and Technology, 16(6), Article 145.
14. Naik, A. V., Sheelam, G. K., Panchakatla, N., Muthukumaran, K., & Saranya, K. (2025). Comprehensive Analysis on Depression Detection From Social Media Using Deep Learning and Transformer Architectures. In 2025 International Conference on Communication, Computer, and Information Technology (IC3IT) (pp. 1–8). IEEE. 2025 International Conference on Communication, Computer, and Information Technology (IC3IT). https://doi.org/10.1109/ic3it66137.2025.11341160
15. Nguyen, C. V., Shen, X., Aponte, R., Xia, Y., Basu, S., Hu, Z., Chen, J., Parmar, M., Kunapuli, S., Barrow, J., Wu, J., Singh, A., Wang, Y., Gu, J., Dernoncourt, F., Ahmed, N. K., Lipka, N., Zhang, R., Chen, X., ... Nguyen, T. H. (2025). A survey on small language models. Recent Advances in Natural Language Processing, 807–821.
16. Mukherjee, S., Mitra, A., Jawahar, G., Agarwal, S., Palangi, H., & Awadallah, A. (2023). Orca: Progressive learning from complex explanation traces of GPT-4. arXiv preprint arXiv:2306.02707.
17. Challa, K., Challa, S. R., Pamisetty, A., Kaulwar, P. K., & Koppolu, H. K. R. (2025, December). Transforming Payments: The Role of AI and Big Data in Fraud Alerts, Credit Monitoring, and Secure Transactions. In 2025 IEEE International Conference on Communication Networks and Computing (CNC) (pp. 1406-1414). IEEE.
18. Zhang, P., Zeng, G., Wang, T., & Lu, W. (2024). TinyLlama: An open-source small language model. arXiv preprint arXiv:2401.02385.
19. Ranaldi, L., & Freitas, A. (2024). Aligning large and small language models via chain-of-thought reasoning. Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics, 1812–1827.
20. Vadisetty, R., Nuka, S. T., Kalisetty, S., Pandugula, C., Burugulla, J. K. R., & Annapareddy, V. N. (2026). and Polypropylene Manufacturing. In Proceedings of Sixth International Ethical Hacking Conference: AI and Law (eHaCON 2025) (p. 269). Springer Nature.
21. Kim, S., Joo, S., Kim, D., Jang, J., Ye, S., Shin, J., & Seo, M. (2023). The CoT Collection: Improving zero-shot and few-shot learning of language models via chain-of-thought fine-tuning. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, 12685–12708.
22. Fan, C., Tian, J., Li, Y., Chen, W., He, H., & Jin, Y. (2023). Chain-of-thought tuning: Masked language models can also think step by step in natural language understanding. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, 14460–14473.
23. Maguluri, K. K. (2026). Cloud-Integrated Machine Learning System for Ebola Virus Disease Prediction and Epidemic Intelligence in Smart Healthcare Systems. Journal of Advances in Management, Engineering and Science (JAMES), 1(03), 1-9.
24. Cheng, X., Li, J., Zhao, W. X., & Wen, J. (2024). ChainLM: Empowering large language models with improved chain-of-thought prompting. Proceedings of the 15th International Conference on Language Resources and Evaluation, 1921–1931.
25. Yang, R., Song, L., Li, Y., Zhao, S., Ge, Y., Li, X., & Shan, Y. (2023). GPT4Tools: Teaching large language model to use tools via self-instruction. Advances in Neural Information Processing Systems, 36.
26. Rajamanickam, V., Singireddy, S., Davuluri, P. N., Sheelam, G. K., Aitha, A. R., & Vakkalagadda, T. (2026). AI-Enabled Visual Evidence Intelligence for Detecting Manipulated Digital Media. International Journal of Special Education, 41(14s), 115-124.
27. Haluptzok, P., Bowers, M., & Kalai, A. T. (2023). Language models can teach themselves to program better. International Conference on Learning Representations.
28. Wang, H., Ma, S., Dong, L., Huang, S., Wang, H., Ma, L., Yang, F., Wang, R., Wu, Y., & Wei, F. (2023). BitNet: Scaling 1-bit transformers for large language models. Proceedings of the International Conference on Learning Representations.
29. Frantar, E., Ashkboos, S., Hoefler, T., & Alistarh, D. (2023). GPTQ: Accurate post-training quantization for generative pre-trained transformers. International Conference on Learning Representations.
30. Davuluri, P. S. L. (2023). AI-Augmented Sanctions Screening: Enhancing Accuracy and Latency in Real Time Compliance Systems. AI-Augmented Sanctions Screening: Enhancing Accuracy and Latency in Real Time Compliance Systems (December 15, 2023).
31. Dettmers, T., Pagnoni, A., Holtzman, A., & Zettlemoyer, L. (2023). QLoRA: Efficient finetuning of quantized LLMs. Advances in Neural Information Processing Systems, 36.
32. Hu, E. J., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., Wang, L., & Chen, W. (2022). LoRA: Low-rank adaptation of large language models. International Conference on Learning Representations.
33. Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., Küttler, H., Lewis, M., Yih, W.-T., Rocktäschel, T., Riedel, S., & Kiela, D. (2020). Retrieval-augmented generation for knowledge-intensive NLP tasks. Advances in Neural Information Processing Systems, 33, 9459–9474.
34. Bedi, B., Yandamuri, U. S., Kummari, D. N., Nagubandi, A. R., & Amistapuram, K. (2026, April). AI-Driven Sentiment and Behavior Analysis for Sustainable Business Growth. In 2026 International Conference on Emerging Research in Smart Electronics and Machine Informatics (ECMI) (pp. 1-11). IEEE.
35. Gao, Y., Xiong, Y., Gao, X., Jia, K., Pan, J., Bi, Y., Dai, Y., Sun, J., Guo, Q., Wang, M., & Wang, H. (2023). Retrieval-augmented generation for large language models: A survey. arXiv preprint arXiv:2312.10997.
36. Asai, A., Wu, Z., Wang, Y., Sil, A., & Hajishirzi, H. (2024). Self-RAG: Learning to retrieve, generate, and critique through self-reflection. International Conference on Learning Representations.
37. Gao, Y., Xiong, Y., Gao, X., Jia, K., Pan, J., Bi, Y., Dai, Y., Sun, J., Guo, Q., Wang, M., & Wang, H. (2024). Retrieval-augmented generation for large language models: A survey. ACM Computing Surveys.
38. Vankayalapati, R. K., Polineni, T. N. S., Ahammad, S. H., Pandugula, C., & Selvan, R. S. (2026). IoT-Enabled Augmented Reality for Real-Time Equipment Diagnosis. In Virtual Reality, Real Emergency (pp. 104-121). CRC Press.
39. Yao, S., Yu, D., Zhao, J., Shafran, I., Griffiths, T. L., Cao, Y., & Narasimhan, K. (2023). Tree of thoughts: Deliberate problem solving with large language models. Advances in Neural Information Processing Systems, 36.
40. Shinn, N., Cassano, F., Gopinath, A., Narasimhan, K., & Yao, S. (2023). Reflexion: Language agents with verbal reinforcement learning. Advances in Neural Information Processing Systems, 36.
41. Wu, Q., Bansal, G., Zhang, J., Wu, Y., Li, B., Zhu, E., Jiang, L., Zhang, X., Zhang, S., Liu, J., Awadallah, A. H., & Wang, C. (2023). AutoGen: Enabling next-generation LLM applications via multi-agent conversation. arXiv preprint arXiv:2308.08155.
42. Hong, S., Zhuge, M., Chen, J., Zheng, X., Cheng, Y., Wang, C., Zhang, Z., Wang, J., Yau, S. K. S., Lin, Z., Zhou, L., Ran, Y., Xiao, C., Wu, C., & Schmidhuber, J. (2024). MetaGPT: Meta programming for a multi-agent collaborative framework. International Conference on Learning Representations.
43. Qian, C., Liu, X., Wang, S., Li, H., Zhu, J., Liu, S., & Zhang, J. (2024). ChatDev: Communicative agents for software development. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics, 151–167.
44. Schick, T., Dwivedi-Yu, J., Dessi, R., Raileanu, R., Lomeli, M., Zettlemoyer, L., Cancedda, N., & Scialom, T. (2024). Tool use and tool learning in large language models. Foundations and Trends in Machine Learning, 17(4), 1–93.
45. Segireddy, A. R., Nagabhyru, K. C., Gadi, A. L., Pandiri, L., Paleti, S., Nandan, B. P., ... & Meda, R. (2026). U.S. Patent Application No. 19/389,116.
46. Qin, Y., Liang, S., Ye, Y., Zhu, K., Yan, L., Lu, Y., Lin, Y., Cong, X., Tang, X., Qian, B., & others. (2024). ToolLLM: Facilitating large language models to master 16000+ real-world APIs. International Conference on Learning Representations.
47. Patil, S. G., Zhang, T., Wang, X., & Gonzalez, J. E. (2023). Gorilla: Large language model connected with massive APIs. Advances in Neural Information Processing Systems, 36.
48. Li, M., Song, F., Yu, B., Yu, H., Li, Z., Huang, F., & Li, Y. (2023). API-Bank: A comprehensive benchmark for tool-augmented LLMs. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, 3102–3116.
49. Deng, Y. (2023). IBM intelligent remediation for ITOps incidents powered by generative AI. NeurIPS 2023 Demonstration Track.
50. Agarwal, P., Dave, H., Bandlamudi, J., Sindhgatta, R., & Mukherjee, K. (2024). Multi-stage prompting for next best agent recommendations in adaptive workflows. Proceedings of the AAAI Conference on Artificial Intelligence, 38(21), 23189–23197.
51. Inala, R., Garapati, R. S., Aitha, A. R., Komaragiri, V. B., Gottimukkala, V. R. R., Recharla, M., ... & Varri, D. B. S. (2026). U.S. Patent Application No. 19/389,108.
52. Zhang, L., Jia, T., Jia, M., Wu, Y., Liu, A., Yang, Y., Wu, Z., Hu, X., Yu, P., & Li, Y. (2025). A survey of AIOps in the era of large language models. ACM Computing Surveys, 58(2), Article 44.
53. Wadhwa, A., Kaur, A., & others. (2024). Large language models for IT operations and AIOps: A systematic review. Journal of Systems and Software, 218, Article 112024.
54. Li, J., Li, G., Zhao, Y., Li, Y., & others. (2024). Large language models for software engineering: A systematic literature review. ACM Transactions on Software Engineering and Methodology, 33(5), Article 128.
55. Hou, X., Zhao, Y., Wang, S., Li, J., & others. (2024). Large language models for software engineering: A systematic literature review. ACM Transactions on Software Engineering and Methodology, 33(5), 1–58.
56. Wang, J., Wei, L., Wang, Z., & others. (2024). Large language models for business process management: Opportunities, challenges, and future directions. Business Process Management Journal, 30(6), 1701–1724.
57. Mendling, J., Decker, G., Hull, R., Reijers, H. A., & Weber, I. (2021). How do machine learning, robotic process automation, and artificial intelligence impact business process management? Communications of the Association for Information Systems, 48, 1–16.
58. van der Aalst, W. M. P. (2021). Process mining: A 360 degree overview. In W. M. P. van der Aalst (Ed.), Process mining handbook (pp. 3–34). Springer.
59. Zhang, L., Wang, S., Li, X., Chen, Y., & others. (2026). Large language model agents for autonomous enterprise workflows: Architectures, orchestration, and governance. Information Systems, 141, Article 102748.
Additional Files
Published
Data Availability Statement
None
Issue
Section
License
Copyright (c) 2026 Ethan Williams (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
This work is licensed under the Creative Commons Attribution 4.0 International License (CC BY 4.0). Authors retain full copyright of their published work. Under this license, others are free to share, copy, distribute, transmit, remix, transform, and build upon the published work for any purpose, including commercial use, provided that appropriate credit is given to the original authors, a link to the license is provided, and any changes made are clearly indicated. No additional restrictions may be applied that limit others from doing anything the license permits. All published articles are freely and permanently accessible online to readers worldwide without any subscription or access fees.
License URL: https://creativecommons.org/licenses/by/4.0/
