Journal Home
Login
Register
Open Access Journal
Submit a Paper
Propose a Special lssue
Open Access
ARTICLE
Integrative Intelligence at the Edge: Converging Large Language Model Multi-Agent Systems, Foundation Models, and Neuromorphic Paradigms for Sustainable and Privacy-Aware Artificial Intelligence
Issue Vol. 2 No. 01 (2025): Volume 02 Issue 01 --- Section Articles
PDF
Abstract
The contemporary evolution of artificial intelligence is characterized by the simultaneous maturation of multiple paradigms that were historically developed in relative isolation. Large language model based multi-agent systems, foundation models for time series and perception, edge intelligence architectures, and neuromorphic computing are now converging within a shared socio-technical context defined by sustainability constraints, privacy regulation, and real-world deployment complexity. This article develops an original, integrative research perspective that theorizes how these paradigms collectively redefine the architecture, governance, and epistemology of intelligent systems. Rather than treating large language models, object detection frameworks, time-series foundation models, and neuromorphic hardware as parallel trends, this work conceptualizes them as interacting layers within a unified intelligence stack spanning cloud, edge, and device-level computation. Drawing exclusively on established scholarly literature, the article advances a text-based analytical methodology to synthesize theoretical foundations, historical trajectories, and emerging challenges across these domains. Particular emphasis is placed on the role of multi-agent coordination among large language models, the long-term evolution of perception systems in computer vision, the environmental and computational implications of green AI benchmarks, and the epistemic shift introduced by foundation models for temporal data. The results of this integrative analysis reveal a set of structural tensions between scalability and efficiency, autonomy and control, and performance and accountability. The discussion critically interrogates these tensions by situating them within broader debates on edge intelligence, neuromorphic design philosophies, regulatory frameworks such as data protection law, and brain-inspired computation. The article concludes by proposing a forward-looking research agenda that emphasizes co-design across algorithms, hardware, and governance structures, arguing that sustainable and trustworthy artificial intelligence will emerge not from isolated optimization but from deliberate integration across conceptual and technological boundaries (Guo et al., 2024; Liang et al., 2024; Deng et al., 2020).
Keywords
References
1. Davies, M., et al. Loihi: A neuromorphic manycore processor with on-chip learning. IEEE Micro, 2018.
2. Voigt, P., & Von dem Bussche, A. The EU General Data Protection Regulation (GDPR): A practical guide. Springer, 2017.
3. Zou, Z., Chen, K., Shi, Z., Guo, Y., & Ye, J. Object detection in 20 years: A survey. Proceedings of the IEEE, 2023.
4. Deng, S., Zhao, H., Fang, W., Yin, J., Dustdar, S., & Zomaya, A. Y. Edge intelligence: The confluence of edge computing and artificial intelligence. IEEE Internet of Things Journal, 2020.
5. Guo, T., Chen, X., Wang, Y., Chang, R., Pei, S., Chawla, N. V., Wiest, O., & Zhang, X. Large language model based multi-agents: A survey of progress and challenges. Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, 2024.
6. Liang, Y., Wen, H., Nie, Y., Jiang, Y., Jin, M., Song, D., Pan, S., & Wen, Q. Foundation models for time series analysis: A tutorial and survey. Proceedings of the ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2024.
7. Liu, Q., Zhu, J., Dai, Q., & Wu, X.-M. Benchmarking news recommendation in the era of green AI. Companion Proceedings of the ACM Web Conference, 2024.
8. Indiveri, G., & Liu, S.-C. Memory and information processing in neuromorphic systems. Proceedings of the IEEE, 2015.
9. Li, G., Deng, L., Tang, H., Pan, G., Tian, Y., Roy, K., & Maass, W. Brain-inspired computing: A systematic survey and future trends. Proceedings of the IEEE, 2024.
10. Satyanarayanan, M., et al. The emergence of edge computing. Computer, 2017.
11. Hua, H., Li, Y., Wang, T., Dong, N., Li, W., & Cao, J. Edge computing with artificial intelligence: A machine learning perspective. ACM Computing Surveys, 2023.
12. Merolla, P. A., et al. A million spiking-neuron integrated circuit with a scalable communication network and interface. Science, 2014.
13. Frenkel, C., Bol, D., &Indiveri, G. Bottom-up and top-down approaches for the design of neuromorphic processing systems. Proceedings of the IEEE, 2023.
