EUVIMEDEUVIMED entdecken
Crossref

Adaptive Multi-Agent AI Framework for Real-Time Data Streaming with Enhanced Scalability and Resilience

Nethmi Perera, Kasun Fernando

American Journal of Applied Science and Technology · 20.08.2026 · 6 (08) · 145-152

DOI: 10.37547/ajast/volume06issue08-10 ↗

Kurz gefasst

Fachartikel in der Zeitschrift American Journal of Applied Science and Technology, online erschienen am 20.08.2026. Verfasst von Nethmi Perera und 1 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Real-time data streaming systems increasingly operate under highly variable workloads, heterogeneous data sources, latency constraints, and frequent service disruptions. Conventional stream-processing architectures generally depend on predefined routing, static resource allocation, and centralized coordination, which can limit their ability to adapt when event rates, computational requirements, or infrastructure conditions change rapidly. This paper proposes an Adaptive Multi-Agent AI Framework for Real-Time Data Streaming with Enhanced Scalability and Resilience, in which autonomous AI agents collaboratively perform stream monitoring, workload classification, task allocation, resource adaptation, anomaly detection, and recovery. The theoretical foundation combines multi-agent coordination with contextual representation, long-document processing, memory management, and adaptive decision-making. Prior work on aspect-controllable summarization demonstrates the value of controlling computational objectives according to task requirements, while studies of coreference, lexical chains, and entity-based coherence emphasize the importance of preserving relationships across distributed information units (Amplayo, Angelidis, & Lapata, 2021; Baldwin & Morton, 1998; Barzilay & Elhadad, 1997; Barzilay & Lapata, 2005). Long-context language modeling further motivates mechanisms capable of retaining relevant information over extended streaming windows (Beltagy, Peters, & Cohan, 2020). The proposed framework extends these principles to adaptive streaming environments and aligns with recent multi-agent event-streaming research emphasizing resiliency and scalability (Reddy et al., 2026). Analytical findings indicate that decentralized agent specialization, shared contextual state, adaptive workload redistribution, and failure-aware coordination can provide a stronger basis for resilient streaming than static pipelines. The paper also identifies trade-offs involving coordination overhead, state consistency, model complexity, and resource consumption.

Zitieren

APA

Perera, N., & Fernando, K. (2026). Adaptive Multi-Agent AI Framework for Real-Time Data Streaming with Enhanced Scalability and Resilience. American Journal of Applied Science and Technology, 6(08), 145-152. https://doi.org/10.37547/ajast/volume06issue08-10

Vancouver

Perera N, Fernando K. Adaptive Multi-Agent AI Framework for Real-Time Data Streaming with Enhanced Scalability and Resilience. American Journal of Applied Science and Technology. 2026;6(08):145-152. doi:10.37547/ajast/volume06issue08-10

BibTeX
@article{Perera2026,
  author = {Perera, Nethmi and Fernando, Kasun},
  title = {Adaptive Multi-Agent AI Framework for Real-Time Data Streaming with Enhanced Scalability and Resilience},
  journal = {American Journal of Applied Science and Technology},
  year = {2026},
  volume = {6},
  number = {08},
  pages = {145--152},
  doi = {10.37547/ajast/volume06issue08-10}
}
Kostenlos starten →