TY - JOUR

T1 - IS TASK-BASED AI THE MISSING LINK BETWEEN HUMAN AND MACHINE REASONING?

AU - Goncharov, Sergey

AU - Vityaev, Evgenii

AU - Sviridenko, Dmitry

AU - Nechesov, Andrey

N1 - Goncharov, S., Vityaev, E., Sviridenko, D. et al. IS TASK-BASED AI THE MISSING LINK BETWEEN HUMAN AND MACHINE REASONING?. J Math Sci 295, 4–14 (2025). https://doi.org/10.1007/s10958-025-08144-x Sergey Goncharov and Evgenii Vityaev thanks for financial support the State Assignment “Logical calculus and Semantics, Model theory and Computability” FWNF-2022-0011.

PY - 2026/1/10

Y1 - 2026/1/10

N2 - We present a comprehensive task-based approach as the foundation for developing explainable and trustworthy AI systems. A task Τ is formally defined as a 6-tuple including Goal, Input, Constraints, Output, verification Criterion, and domain Ontology. The framework emphasizes hierarchical decomposition, where complex goals are broken into verifiable subtasks, enabling traceable, human-interpretable explanations through satisfaction proofs (πi) for each criterion Κi. It integrates symbolic reasoning and probabilistic learning via functional systems, hierarchies, and semantic probabilistic inference for the knowledge induction. The approach supports hybrid multi-agent systems, combining LLMs for goal-oriented reasoning with logic-based agents for constraint enforcement. The key design principles ensure task-centric architecture, explicit criteria, ontological alignment, and criterion-centric explanations. Validation across diverse domains demonstrates its capacity to deliver mathematically verifiable, robust, and auditable AI solutions. Bibliography: 28 titles. Illustrations: 3 figures.

AB - We present a comprehensive task-based approach as the foundation for developing explainable and trustworthy AI systems. A task Τ is formally defined as a 6-tuple including Goal, Input, Constraints, Output, verification Criterion, and domain Ontology. The framework emphasizes hierarchical decomposition, where complex goals are broken into verifiable subtasks, enabling traceable, human-interpretable explanations through satisfaction proofs (πi) for each criterion Κi. It integrates symbolic reasoning and probabilistic learning via functional systems, hierarchies, and semantic probabilistic inference for the knowledge induction. The approach supports hybrid multi-agent systems, combining LLMs for goal-oriented reasoning with logic-based agents for constraint enforcement. The key design principles ensure task-centric architecture, explicit criteria, ontological alignment, and criterion-centric explanations. Validation across diverse domains demonstrates its capacity to deliver mathematically verifiable, robust, and auditable AI solutions. Bibliography: 28 titles. Illustrations: 3 figures.

UR - https://www.mendeley.com/catalogue/6ffa6243-b04b-3aa9-8871-7462a0c0f51d/

UR - https://www.scopus.com/pages/publications/105031476090

U2 - 10.1007/s10958-025-08144-x

DO - 10.1007/s10958-025-08144-x

M3 - Article

VL - 295

SP - 4

EP - 14

JO - Journal of Mathematical Sciences (United States)

JF - Journal of Mathematical Sciences (United States)

SN - 1072-3374

ER -