AI-Enabled Multi-Agent Approach for Reliable and High-Performance Event Stream Management
Keywords:
Multi-Agent Systems, Artificial Intelligence, Event Stream Management, Generalized PlanningAbstract
The increasing volume, velocity, and heterogeneity of event streams require intelligent management mechanisms capable of maintaining throughput, responsiveness, scalability, and operational reliability under continuously changing workloads. Conventional stream-processing architectures generally rely on predetermined routing, scheduling, and resource-management policies, which can become inefficient when event arrival rates, computational requirements, and system conditions change dynamically. This paper proposes a conceptual AI-enabled multi-agent approach for reliable and high-performance event stream management, integrating symbolic planning, learned representations, policy generation, temporal reasoning, and decentralized agent coordination. The theoretical foundation is derived exclusively from the supplied literature on planning, generalized policies, first-order representations, sketches, temporal logic, and description-logic state features. The proposed architecture models stream-management functions as interacting intelligent agents responsible for event observation, workload characterization, resource allocation, routing, fault adaptation, and policy refinement. The analysis indicates that combining learned state representations with generalized planning policies can improve adaptability while reducing dependence on manually specified control rules. Temporal reasoning further provides a basis for deadline-aware and sequence-sensitive stream decisions, whereas planning sketches can constrain decision complexity in large operational spaces. The study positions multi-agent event stream management as a synthesis of symbolic planning and adaptive AI rather than as a purely reactive stream-processing mechanism. The principal contribution is a research framework that links representation learning, generalized planning, temporal control, and resilient coordination into a unified model for event-stream environments.
Downloads
References
1. Asai, M. (2019). Unsupervised grounding of plannable first-order logic representation from images.In Lipovetzky, N., Onaindia, E., & Smith, D. E. (Eds.),Proceedings of the Twenty-NinthInternational Conference on Automated Planning and Scheduling (ICAPS 2019), pp. 583–591. AAAI Press.
2. Baader, F., Calvanese, D., McGuinness, D. L., Nardi, D., & Patel-Schneider, P. F. (Eds.). (2003).The Description Logic Handbook: Theory, Implementation and Applications. CambridgeUniversity Press.
3. Bacchus, F. (2001). The AIPS’00 planning competition.AI Magazine,22(3), 47–56.
4. Bacchus, F., & Kabanza, F. (2000). Using temporal logics to express search control knowledge for planning. Artificial Intelligence,116(1–2), 123–191.
5. Baier, J. A., Fritz, C., Bienvenu, M., & McIlraith, S. A. (2008). Beyond classical planning: Proce-dural control knowledge and preferences in state-of-the-art planners. InProceedings of theTwenty-Third AAAI Conference on Artificial Intelligence (AAAI 2008), pp. 1509–1512. AAAIPress.
6. Bonet, B., Franc`es, G., & Geffner, H. (2019). Learning features and abstract actions for computing generalized plans. In Proceedings of the Thirty-Third AAAI Conference on Artificial Intelli-gence (AAAI 2019), pp. 2703–2710. AAAI Press.
7. Bonet, B., & Geffner, H. (2018). Features, projections, and representation change for generalized planning. In Lang, J. (Ed.),Proceedings of the 27th International Joint Conference on Artifi-cial Intelligence (IJCAI 2018), pp. 4667–4673. IJCAI.
8. Bonet, B., & Geffner, H. (2020a). Learning first-order symbolic representations for planning fromthe structure of the state space. In De Giacomo, G. (Ed.),Proceedings of the 24th EuropeanConference on Artificial Intelligence (ECAI 2020), pp. 2322–2329. IOS Press.
9. Bonet, B., & Geffner, H. (2020b). Qualitative numeric planning: Reductions and complexity.Jour-nal of Artificial Intelligence Research,69, 923–961.
10. Bonet, B., & Geffner, H. (2021). General policies, representations, and planning width. In Leyton-Brown, K., & Mausam (Eds.),Proceedings of the Thirty-Fifth AAAI Conference on ArtificialIntelligence (AAAI 2021), pp. 11764–11773. AAAI Press.
11. Daggelinckx, A. (2023). Generating and verifying planning sketches using temporal logic. Master’sthesis, Utrecht University.
12. Dalmau-Moreno, M., Garc ́ıa, N., G ́omez, V., & Geffner, H. (2023). Combined task and motionplanning via sketch decompositions. InICAPS 2023 Planning and Robotics Workshop (Plan-Rob).
13. Drexler, D., Franc`es, G., & Seipp, J. (2022). Description logics state features for planning (DLPlan).
14. Drexler, D., Seipp, J., & Geffner, H. (2021). Expressing and exploiting the common subgoal struc-ture of classical planning domains using sketches. In Erdem, E., Bienvenu, M., & Lakemeyer,G. (Eds.),Proceedings of the Eighteenth International Conference on Principles of Knowl-edge Representation and Reasoning (KR 2021), pp. 258–268. IJCAI Organization.
15. Drexler, D., Seipp, J., & Geffner, H. (2022). Learning sketches for decomposing planning problemsinto subproblems of bounded width. In Thi ́ebaux, S., & Yeoh, W. (Eds.), Proceedings ofthe Thirty-Second International Conference on Automated Planning and Scheduling (ICAPS2022), pp. 62–70. AAAI Press.
16. R. Reddy, P. Udayaraju, K. K. Goyal, S. C. R. Vudem, R. Sayana and V. Gummadi, "Creating an AI-based Multi-Agent Model for Optimized Data Streaming with Improved Resiliency and Scalability for Event Streaming," 2026 6th International Conference on Image Processing and Capsule Networks (ICIPCN), Dhulikhel, Nepal, 2026, pp. 1372-1379, doi: 10.1109/ICIPCN67432.2026.11438445.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Arjun Sharma, Priya Mehta (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
All articles published by The Parthenon Frontiers and its associated journals are distributed under the terms of the Creative Commons Attribution (CC BY 4.0) International License unless otherwise stated.
Authors retain full copyright of their published work. By submitting their manuscript, authors agree to grant The Parthenon Frontiers a non-exclusive license to publish, archive, and distribute the article worldwide. Authors are free to:
-
Share their article on personal websites, institutional repositories, or social media platforms.
-
Reuse their content in future works, presentations, or educational materials, provided proper citation of the original publication.
