ADAPTIVE COMPUTING STRUCTURES FOR SERVICE-ORIENTED MULTI-AGENT SYSTEMS BASED ON KNOWLEDGE MODELS

Vadim Struna; Victor Ababii; Viorica Sudacevschi; Silvia Munteanu; Olesea Borozan; Victoria Alexei

doi:10.52326/jes.utm.2026.33(1).03

Authors

Vadim Struna Technical University of Moldova, 168, Ștefan cel Mare Blvd., Chisinau, Republic of Moldova https://orcid.org/0000-0001-6579-3054
Victor Ababii Technical University of Moldova, 168, Ștefan cel Mare Blvd., Chisinau, Republic of Moldova https://orcid.org/0000-0002-0769-8144
Viorica Sudacevschi Technical University of Moldova, 168, Ștefan cel Mare Blvd., Chisinau, Republic of Moldova https://orcid.org/0000-0003-0125-3491
Silvia Munteanu Technical University of Moldova, 168, Ștefan cel Mare Blvd., Chisinau, Republic of Moldova https://orcid.org/0000-0003-0749-8457
Olesea Borozan Technical University of Moldova, 168, Ștefan cel Mare Blvd., Chisinau, Republic of Moldova https://orcid.org/0000-0003-1091-5506
Victoria Alexei Technical University of Moldova, 168, Ștefan cel Mare Blvd., Chisinau, Republic of Moldova https://orcid.org/0000-0003-4560-3131

DOI:

https://doi.org/10.52326/jes.utm.2026.33(1).03

Keywords:

conscious–subconscious processing, cognitive architectures, distributed intelligence, heterogeneous hardware, hierarchical computing, knowledge models, mathematical modeling, physiology of the human brain

Abstract

This paper proposes an adaptive computing framework for service-oriented multiagent systems, based on knowledge models inspired by the hierarchical organization of the human brain. The approach integrates neurophysiological principles of conscious and subconscious processing with rigorous mathematical formalization and hardware-oriented architectural design. The conscious–subconscious interaction is modeled as a two-level computational hierarchy, in which subconscious processing is fast, parallel, adaptive, and high-dimensional, and conscious processing is deliberative, symbolic, and low-dimensional, being responsible for control, planning, and decision-making. An attention-based coupling mechanism controls the flow of information between the two levels, allowing for dynamic adaptation and efficient use of resources. Based on this model, a heterogeneous hardware architecture is proposed that maps subconscious processing to NPU/GPU accelerators, and conscious processing to CPU units. The framework is extended to multi-agent systems, in which each agent implements a conscious–subconscious hierarchy, and the emergent coordination is achieved through a collective conscious level. The approach supports distributed intelligence, scalability, and adaptive service composition.

References

Borangiu, T.; Trentesaux, D.; Leitão, P.; Cardin, O.; & Lamouri, S. (Eds.). (2021). Service Oriented, Holonic and Multi-Agent Manufacturing Systems for Industry of the Future: Proceedings of SOHOMA 2020 (Vol. 952). Springer Nature, 544 p., https://doi.org/10.1007/978-3-030-69373-2.

Li, A.; Xie, Y.; Li, S.; Tsung, F.; Ding, B.; & Li, Y. (2024). Agent-oriented planning in multi-agent systems. arXiv preprint arXiv:2410.02189, https://doi.org/10.48550/arXiv.2410.02189.

Wold, H. (1982). Models for knowledge. The making of statisticians, pp. 189-212, Springer, New York, NY. https://doi.org/10.1007/978-1-4613-8171-6_14.

Antonelli, C. (2005). Models of knowledge and systems of governance. Journal of institutional economics, 1(1), pp. 51-73, https://doi.org/10.1017/S1744137405000044.

Munir, K.; & Anjum, M. S. (2018). The use of ontologies for effective knowledge modelling and information retrieval. Applied computing and informatics, 14(2), pp. 116-126, https://doi.org/10.1016/j.aci.2017.07.003.

Haslinda, A.; Sarinah, A. (2009). A review of knowledge management models. Journal of international social research, 2(9), pp. 187, ISSN 1307-9581.

Noy, N.F.; Fergerson, R.W.; Musen, M.A. (2000). The knowledge model of Protégé-2000: Combining interoperability and flexibility. In International conference on knowledge engineering and knowledge management, pp. 17-32, Berlin, Heidelberg: Springer Berlin Heidelberg, https://doi.org/10.1007/3-540- 39967-4_2.

Ababii, V.; Sudacevschi, V.; Munteanu, S.; Carbune, V.; Borozan, O. (2025) Multi-Coalition Multi-Agent decision making system synthesis. In International Journal of Computing, 24(3), pp. 513-519, ISSN 1727-6209, https://doi.org/10.47839/ijc.24.3.4188.

Ababii, V.; Cărbune, V.; Sudacevschi, V.; Marusic, G.; Braniște, R.; Drumea, N. (2025) Sistem Multi-Agent pentru monitorizarea și predicția proceselor de mediu. Akademos, 1(76), pp. 22-30, https://doi.org/10.52673/18570461.25.1-76.01.

Struna, V.; Borozan, O.; Carauș, A. (2023) Knowledge models for evolutionary systems with artificial intelligence. In Proceedings of the Twelfth Conference ”Informatics and Computer Technologies Problems” (ICTP – 2023), pp. 38-41, Chernivtsi, Ukraine, 10-12 November, 2023.

Ababii, V.; Strună, V.; Sudacevschi, V.; Borozan, O.; Munteanu, S. (2024) Method for knowledge acquisition based on image processing for decision-making systems. In Electronics, Communications and Computing (IC ECCO-2024): The conference program and abstract book: 13th intern. conf., pp. 165-166, Chișinău: Tehnica-UTM, 17-18 Oct. 2024. Technical University of Moldova, ISBN: 978-9975-64-480-8 (PDF).

Struna, V.; Ursu A.; Kapusteanski, M. (2024) Analiza modelelor de cunoștințe pentru sisteme cu inteligență artificială. In Technical Scientific Conference of Undergraduate, Master and PhD Students, Universitatea Tehnică a Moldovei, 27-29 Martie 2024. Chișinău, 2024, vol. 1, pp. 392-394. ISBN 978-9975- 64-458-7, ISBN 978-9975-64-459-4.

Baars, B. J.; Franklin, S.; Ramsoy, T. Z. (2013) Global workspace dynamics: Cortical “binding and propagation” enables conscious contents. Frontiers in Psychology, 4, 200. https://doi.org/10.3389/fpsyg.2013.00200.

Clark, A. (2016) Surfing Uncertainty: Prediction, Action, and the Embodied Mind. Oxford University Press. https://doi.org/10.1093/acprof:oso/9780190217013.001.0001.

Damasio, A. (2018) The Strange Order of Things: Life, Feeling, and the Making of Cultures. NY: Pantheon Books, 336p.

Dehaene, S. (2014) Consciousness and the Brain: Deciphering How the Brain Codes Our Thoughts. Viking Press, 363p., ISBN: 978-0-698-15140-6.

Friston, K. (2019) A free energy principle for a particular physics. arXiv preprint, arXiv:1906.10184. https://doi.org/10.48550/arXiv.1906.10184.

Gazzaniga, M. S.; Ivry, R. B.; Mangun, G. R. (2019) Cognitive Neuroscience: The Biology of the Mind (5th ed.). W. W. Norton & Company, ISBN: 978-0-393-60317-0.

Kandel, E. R.; Koester, J. D.; Mack, S. H.; Siegelbaum, S. A. (2021) Principles of Neural Science (6th ed.). McGrawHill Education, 108p., ISBN: 978-1-25-964224-1.

Mashour, G. A.; Roelfsema, P.; Changeux, J.-P.; Dehaene, S. (2020) Conscious processing and the global neuronal workspace hypothesis. Neuron, 105(5), pp. 776-798. https://doi.org/10.1016/j.neuron.2020.01.026.

Pessoa, L. (2017) A network model of the emotional brain. Trends in Cognitive Sciences, 21(5), pp. 357–371. https://doi.org/10.1016/j.tics.2017.03.002.

Seth, A. K.; Bayne, T. (2022) Theories of consciousness. Nature Reviews Neuroscience, 23, pp. 439–452. https://doi.org/10.1038/s41583-022-00587-4.

Stanley, D. A.; Adolphs, R. (2013) Toward a neural basis for social behavior. Neuron, 80(3), pp. 816–826. https://doi.org/10.1016/j.neuron.2013.10.038.

Tononi, G.; Boly, M.; Massimini, M.; Koch, C. (2016) Integrated information theory: From consciousness to its physical substrate. Nature Reviews Neuroscience, 17(7), pp. 450–461. https://doi.org/10.1038/nrn.2016.44.

Friston, K. (2010) The free-energy principle: A unified brain theory? Nature Reviews Neuroscience, 11(2), pp. 127–138. https://doi.org/10.1038/nrn2787

ADAPTIVE COMPUTING STRUCTURES FOR SERVICE-ORIENTED MULTI-AGENT SYSTEMS BASED ON KNOWLEDGE MODELS

Authors

DOI:

Keywords:

Abstract

References

Downloads

Published

How to Cite

Issue

Section

Categories

License

Current Issue

Information