A Sustainable Approach to Personalized Practical Learning Based on Formal Models and AI

This article presents a sustainable, system-level approach to personalized practical learning in digital education environments based on tightly integrating formal models of practical tasks and artificial intelligence technologies. The authors resolve the limitations of current methods in e-learning personalization—such as lack of scalability, insufficient adaptability, and unreliable automation—by introducing an improved application which uses Belief–Desire–Intention (BDI) multi-agent system with adaptive orchestration and domain-specific language of formal practical task specification in the framework of an AI assistant, based on service-oriented architecture (SOA). The proposed approach provides automation for the entire lifecycle of practical tasks, encompassing generation, parameterization, and deployment of a virtual run-time environment and result verification for correctness, reproducibility, and academic integrity. Experimental tests demonstrate that combining a large language model (LLM) with dynamic verification significantly outperforms traditional purely generative approaches in terms of reliability, scalability, and reduction in instructor workload, as well as contributing to more effective task performance by students in practice-oriented learning scenarios. The study concludes that the synergistic integration of formal control mechanisms and AI-driven adaptivity offers a robust foundation for building sustainable smart environments for digital learning ecosystems.