Academic Journal

Adaptive computing structures for service-oriented multi-agent systems based on knowledge models

Bibliographic Details
Title: Adaptive computing structures for service-oriented multi-agent systems based on knowledge models
Authors: Strună, V., Ababii, V.V., Абабий, В., Sudacevschi, V.M., Sudacevschi, V., Судачевски, В., Munteanu, S., Мунтяну, С., Borozan, O., Борозан, О., Alexei, V., Алексей, В.
Source: Journal of Engineering Science (1) 37-52
Publication Year: 2026
Subject Terms: conscious–subconscious processing, cognitive architectures, distributed intelligence, heterogeneous hardware, hierarchical computing, knowledge models, mathematicalmodeling, physiology of the human brain
Description: 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 consciousndash;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 consciousndash;subconscious hierarchy, and the emergent coordination is achieved through a collective conscious level. The approach supports distributed intelligence, scalability, and adaptive service composition.
Document Type: article in journal/newspaper
File Description: application/pdf
Language: English
ISSN: 25873474
Relation: info:eu-repo/grantAgreement/EC/FP7/17730/EU/Inovații în Ingineria Biomedicală: Tehnologii și Aplicații Avansate de Achiziție, Prelucrare și Analiză a Datelor/020404; https://ibn.idsi.md/vizualizare_articol/251758; urn:issn:25873474
DOI: 10.52326/jes.utm.2026.33(1).03
Availability: https://ibn.idsi.md/vizualizare_articol/251758
https://doi.org/10.52326/jes.utm.2026.33(1).03
Rights: info:eu-repo/semantics/openAccess
Accession Number: edsbas.A46A2093
Database: BASE
Description
ISSN:25873474
DOI:10.52326/jes.utm.2026.33(1).03