Interoperable Control in the IoT Computational Continuum with AI Agents
Abstract
The growing adoption of smart agriculture as a response to increasing demands for productivity, product quality, and efficient use of natural resources requires increasingly advanced and resilient cyber-physical infrastructures. In this context, one of the main infrastructure and computing challenges is to ensure interoperability, low latency, and reliability in systems distributed across the IoT–edge–cloud continuum. The literature has addressed these challenges through cloud architectures, edge computing, digital twins, and IoT technologies, which remain largely fragmented and dependent on ad hoc integrations. This work proposes an interoperable multi-agent edge architecture based on Large Language Models (LLMs) and the Model Context Protocol (MCP) to integrate decision-making, monitoring, and actuation in a coordinated manner. Experimental results show that, compared with a structured controller, the LLM-based approach improves diagnostic flexibility in context-dependent scenarios, at the cost of higher latency and resource consumption.
References
Domínguez-Bolaño, T., Campos, O., Barral, V., Escudero, C. J., and García-Naya, J. A. (2022). An overview of iot architectures, technologies, and existing open-source projects. Internet of Things, 20:100626.
Escribà-Gelonch, M., Liang, S., van Schalkwyk, P., Fisk, I., Long, N. V. D., and Hessel, V. (2024). Digital twins in agriculture: orchestration and applications. Journal of agricultural and food chemistry, 72(19):10737–10752.
Ferrag, M. A., Tihanyi, N., Hamouda, D., Maglaras, L., Lakas, A., and Debbah, M. (2025). From prompt injections to protocol exploits: Threats in llm-powered ai agents workflows. ICT Express.
He, Q., Zhao, H., Feng, Y., Wang, Z., Ning, Z., and Luo, T. (2024). Edge computing-oriented smart agricultural supply chain mechanism with auction and fuzzy neural networks. Journal of Cloud Computing, 13(1):66.
Heideker, A., Ottolini, D., Zyrianoff, I., Neto, A. T., Salmon Cinotti, T., and Kamienski, C. (2020). Iot-based measurement for smart agriculture. In 2020 IEEE International Workshop on Metrology for Agriculture and Forestry (MetroAgriFor), pages 68–72.
Jennings, C. F., Shelby, Z., Arkko, J., Keränen, A., and Bormann, C. (2018). Sensor Measurement Lists (SenML). RFC 8428.
Kalyani, Y., Velasco Bermeo, N., and Collier, R. (2023). Digital twin deployment for smart agriculture in cloud-fog-edge infrastructure. International Journal of Parallel, Emergent and Distributed Systems.
Kapitan, D., Heddema, F., Dekker, A., Sieswerda, M., Verhoeff, B.-J., and Berg, M. (2025). Data interoperability in context: The importance of open-source implementations when choosing open standards. J Med Internet Res, 27:e66616.
Kasera, R. K. and Acharjee, T. (2024). A comprehensive iot edge based smart irrigation system for tomato cultivation. Internet of Things, 28:101356.
Kimovski, D., Saurabh, N., Jansen, M., Aral, A., Al-Dulaimy, A., Bondi, A. B., Galletta, A., Papadopoulos, A. V., Iosup, A., and Prodan, R. (2023). Beyond von neumann in the computing continuum: Architectures, applications, and future directions. IEEE Internet Computing, 28(3):6–16.
Kong, L., Tan, J., Huang, J., Chen, G., Wang, S., Jin, X., Zeng, P., Khan, M., and Das, S. K. (2022). Edge-computing-driven internet of things: A survey. ACM Computing Surveys, 55(8).
LF Projects, L. (2026). Model context protocol. [link] Acesso em 31 jan. 2026.
Oliveira, F. B., Di Felice, M., and Kamienski, C. (2024). Iotdeploy: Deployment of iot smart applications over the computing continuum. Internet of Things, 28:101348.
UFABC (2026). Smart: Sustainable management of agriculture with the intelligent computing continuum. [link] Acesso em 31 jan. 2026.
Urdu, D., Berre, A. J., Sundmaeker, H., Rilling, S., Roussaki, I., Marguglio, A., Doolin, K., Zaborowski, P., Atkinson, R., Palma, R., et al. (2024). Aligning interoperability architectures for digital agri-food platforms. Computers and Electronics in Agriculture, 224:109194.
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, Ł., and Polosukhin, I. (2017). Attention is all you need. Advances in neural information processing systems, 30.
Zyrianoff, I., Heideker, A., Silva, D., Kleinschmidt, J. H., Soininen, J.-P., Salmon Cinotti, T., and Kamienski, C. (2020). Architecting and deploying iot smart applications: A performance–oriented approach. Sensors, 20(1):84.
