Intelligent Automation: Multi-Agent AI for Enterprise IT Service Management
Keywords:
Multi-Agent AI Systems, Autonomous Handling, IT Service Requests, Incident Management Automation, Service Request Mitigation, Service Request Fulfillment, ITSM Automation, ITIL Autonomous Request Handling, ITSIAM, Artificial Intelligence as a Service, Non-Intrusive, Integration with ITSM Frameworks.Abstract
Development of Multi-Agent Systems capable of partially or fully automating IT incident response, service request fulfilment or routing across the agent lifecycle, for integration into existing enterprise toolchains and alignment with ITIL across both DevOps and IT Service Management seams. Active experimentation underpins performance evaluation and identifies critical non-functional dimensions: Reliability, robustness, fault tolerance. Performance matches established benchmarks where applicable; incident automation and mitigation, and service request fulfilment and routing for unsupported categories remain areas for ongoing development.
Ongoing Development of a Multi-Agent System capable of autonomously handling enterprise IT service requests. Component agents operate as virtual analysts, equipped to automate service fulfilment, fulfilment-orchestrate routing, or detect & mitigate incident effects – commonly without human involvement. Continuous Improvement promulgates operational agents’ hard-won experience, simultaneously bolstering robustness, broadening capability and confirming normative behaviour for integration-testing seeker agents. Seamless ITIL alignment drives current service request fulfilment; applicable Service Transition activities support experimental automation of incident response and mitigation. Active experimentation probes critical non-functional dimensions: Reliability, robustness, fault tolerance. Continuously-evolving performance meets established benchmarks where applicable; incident automation & mitigation, and service request fulfilment for unsupported categories remain areas for ongoing development.
References
[1]Ademaj, S., Ghanbari, A., Tordsson, J. (2020). Intelligent agents in IT Service Management: A literature survey and agent framework. Future Generation Computer Systems, 113, 558–574.
[2]Akkermans, M. A. (2018). Agents as partners for IT Service Management. The Fifth International Workshop on Agents and Artificial Intelligence (ICAART), 249–256.
[3]Akkermans, M. A., Van Kralingen, C. (2019). Towards a Multi-Agent System for ITIL-based Incident Management. Lecture Notes in Computer Science, 11782, 187–203.
[4]Akkermans, M. A., Van Kralingen, C., Özdemir, B. A., Zeng, Y., Oliva, A. (2020). Multi-Agent AI for Routing and Fulfilment of Service Requests in IT Service Management. Proceedings of the Eleventh International Conference on Advances in Computing, Electronics and Communication (ACECC 2020), 55–60.
[5]Akkermans, M. A., Zeng, Y., Özdemir, B. A. (2021). Multi-Agent AI for Automated Handling of ITSM Service Requests and Incidents. Proceedings of the 24th International Conference on Intelligent Systems and Applications (INTELLI 2021), 163–170.
[6]Becker, H., Ziegler, J. (2022). Agents for IT Service Management: An Empirical Study. Proceedings of the 28th International Conference on Computational Intelligence (ICCI 2022), 91–98.
[7]Cohen, C. S., Vicknair, J. (2020). A Survey of Multi-Agent Systems in IT Service Management. Proceedings of the 8th Annual ACM Midwest Computer Conference, 107–111.
[8]Governatori, G. (2018). Intelligent agents in ITIL: the service strategy process. Proceedings of the 16th International Conference on Artificial Intelligence and Expert Systems, 222–234.
[9]Hypertext Transfer Protocol -- HTTP/2 (2015). IETF RFC 7540.
[10]Pelechrinis, K., Koutsopoulos, I., Kallem, S. (2011). Network-resilience to interdependent failures: A study of critical infrastructures. IEEE 2nd International Conference on Cloud Computing and Intelligence Systems (CCIS 2011), 403–407.
[11]Bai, Z., Ge, E., & Hao, J.Multi-agent collaborative framework for intelligent IT operations: An AOI system with context-aware compression and dynamic task scheduling. arXiv preprint.
[12]Borkowski, A. A., et al.. Multiagent AI systems in health care: Envisioning next-generation intelligent systems. Journal of Medical Systems, 49(2), 1–15.
[13]Han, S., et al. (2024). LLM-based multi-agent systems: Challenges and open problems. arXiv preprint.
[14]Krishnan, N. Advancing multi-agent systems through model context protocol: Architecture, implementation, and applications. arXiv preprint.
[15]Liu, Y., Lo, S. K., Lu, Q., Zhu, L., Zhao, D., Xu, X., Harrer, S., & Whittle, J. Agent design pattern catalogue: A collection of architectural patterns for foundation model-based agents. Journal of Systems and Software, 220, 112278.
[16]Lu, J., Pan, B., Chen, J., Feng, Y., Hu, J., Peng, Y., & Chen, W. (2024). AgentLens: Visual analysis for agent behaviors in LLM-based autonomous systems. IEEE Transactions on Visualization and Computer Graphics, 31(8), 4182–4197.
[17]Luzolo, P. H. (2024). Combining multi-agent systems and artificial intelligence: A distributed approach for complex problem solving. Journal of Systems Architecture, 152, 102456.
[18]Mu, C., Guo, H., Chen, Y., Shen, C., Hu, D., Hu, S., & Wang, Z. (2024). Multi-agent, human-agent and beyond: A survey on cooperation in social dilemmas. Neurocomputing, 610, 128514.
[19]Olujimi, P. A., et al.Agentic AI frameworks in SMMEs: A systematic literature review. AI, 6(6), 123.
[20]Raza, S., Sapkota, R., Karkee, M., & Emmanouilidis, C.TRiSM for agentic AI: Trust, risk, and security management in LLM-based multi-agent systems. arXiv preprint.
Additional Files
Published
Data Availability Statement
None
