Immersive learning using Virtual Reality (VR) has gained prominence for delivering experiential, engaging education. However, most VR learning environments lack real-time adaptability, personalization, and cognitive responsiveness. This study presents an Agentic AI-enabled VR framework that autonomously adjusts pedagogical content, interaction style, and challenge level based on learner behavior, emotions, and performance feedback. The proposed system integrates a reinforcement learning-based agent with a virtual reality module to form an intelligent tutor capable of independent decision-making. A neuro-symbolic model processes multi-modal feedback (gesture, speech, gaze, performance) to determine context-aware pedagogical strategies. The system employs a self-evolving curriculum logic that adapts in real time. Experiments are conducted using Unity3D integrated with Python-based RL agents and simulated student models. Results demonstrate a 35.7% improvement in learner retention and a 42.1% reduction in cognitive overload compared to traditional static VR systems. The agent successfully personalized 92.3% of scenarios without human intervention. Emotional adaptivity and dynamic pacing showed increased engagement and reduced frustration metrics among diverse learners. Agentic VR represents a paradigm shift in intelligent education systems, enabling autonomous, emotionally-aware, and responsive learning environments. The proposed framework outperforms conventional VR platforms by offering real-time adaptive learning without pre-scripted logic. Integrating reinforcement learning, neuro-symbolic reasoning, and affective feedback into a single VR space results in a novel contribution to adaptive educational technology. The reported metrics were obtained from an administrator-controlled user study of 10 participants (aged 18 - 25 years), all of whom participated in three VR-based learning experiences as described in a controlled evaluative protocol. This study provides a foundation for future work on autonomous agents in educational met verses, special education, and lifelong learning systems.

Real-time threat detection is crucial in domains like cybersecurity, surveillance, and public safety in general, where quick and effective detection of risks is critical. Current detection approaches suffer from limitations such as high latency, in-processing multi-modal data efficiently, and learning to adapt to evolvement of threats. Therefore, this paper proposes a new algorithm called Adaptive Multi-Modal Neural Network, or simply AMM-Net for a novel neural network algorithm for overcoming the above-listed limitations. AMM-Net incorporates the use of CNNs, RNNs, and transformers in fusing visual, sequential, and textual data streams. Its use of a dynamic attention-based fusion layer allows it to dynamically focus on the most relevant features across modalities for an efficient detection in a myriad and complex scenario. Techniques that aid in real-time deployment through the use of model pruning, quantization, and edge computing will further make it deployable to resource-constrained environments.

Globally, solar energy has garnered considerable attention, securing the third position among energy sources, trailing behind wind and hydropower. This study aims to assess the solar power potential by examining the performance disparities between a Static Solar System (SSS) and a Dual Axis Solar Tracker (DAST). Solar irradiance, analysed for both clear and cloudy days using sun angles such as zenith and solar altitude, served to identify solar power capabilities. The study further measured the cumulative energy generation on a daily basis throughout the month. To offer a comprehensive perspective, the research delved into variations in efficiency on a daily and monthly basis. The outcomes, presented through tables and graphs, unequivocally demonstrate that the suggested tracking system outperforms the Static Solar System (SSS) significantly in terms of energy gain and efficiency.

Augmented reality and virtual reality are changing the healthcare sector, allowing for more immersive and interactive solutions for remote patient care and medical training. These technologies have opened new possibilities for telemedicine—new ways of delivering treatments in real-time and monitoring patients, for example. However, the challenges for AR/VR systems include the real-time integration of data from IoT-enabled medical devices and ensuring the security and privacy of sensitive patient data. This paper presents a cutting-edge AI-enhanced framework for AR/VR in remote healthcare to address these critical issues. It integrates edge computing to ensure minimal latency and system responsiveness; blockchain technology to secure the transaction of data; and federated learning to train AI models while maintaining the privacy of patients. Leveraging the advanced capabilities of the HTC VIVE Pro 2 kit, the framework supports several applications, including remote physiotherapy, surgical guidance, and real-time health monitoring. All the developed applications are tested in simulated real-world scenarios to check the performance of the system in terms of latency, adaptability, security, and user satisfaction. The experiments conducted show vast improvements in terms of data transmission efficiency, system robustness, and user engagement as a whole, proving that the proposed solution is very feasible and scalable. Hence, the research conducted signifies the significance of integrating AI, IoT, and AR/VR to address healthcare issues, paving the way for future breakthroughs. This research contributes to a new frontier for patient-centric, data-driven, and highly interactive healthcare systems by laying a secure and intelligent base platform for remote care.

The rapid growth of photovoltaic (PV) installations demands intelligent, transparent, and resilient control frameworks that can adapt to fluctuating atmospheric and grid conditions. Conventional digital twin solutions, though effective in monitoring and forecasting, often fall short when facing sensor degradation, communication noise, or operator workload challenges. Their static architectures and narrowly scoped machine learning models typically lack both adaptive resilience and seamless integration of human oversight—critical requirements for mission-essential PV systems. To overcome these limitations, we introduce a Cognitive Digital Twin with Virtual Reality (CDT–VR), a framework that combines physics-informed models, deep learning surrogates, and reinforcement learning–based policy control. The design incorporates hybrid-fidelity monitoring, real-time drift detection, and immersive VR interfaces, enabling operators to validate or adjust system trajectories interactively through explainable overlays. This dual focus on algorithmic robustness and operator usability distinguishes CDT–VR from prior digital twin deployments in solar energy. Experimental results demonstrate forecasting accuracy with NRMSE as low as 8.9%, drift detection within 90 seconds, and P95 response latency of 382 ms, ensuring grid-compliant performance. Furthermore, operator studies using VR interfaces revealed a 27% reduction in task completion time and a 22% decrease in workload compared with conventional SCADA platforms. By unifying adaptive control with human-in-the-loop decision support, CDT–VR establishes a resilient pathway for digital twin deployment in renewable energy operations, with broader relevance to smart grids and critical cyber-physical infrastructures.

The deep learning (DL) and blockchain technology's integration can revolutionize the agriculture system, especially in the case of improving precision farming systems. In this paper, we propose a new conceptual framework that combines the latest developed deep learning capabilities for real time data evaluation with centralized and decentralized blockchain platforms for agro-food smart functions. IoT-orchestrated data is a driver of the new paradigm of precision farming facilitating maximization of crop production while ensuring minimum wastage of input resources and enhancing decision making. However, challenges such as data quality, secure data transfer, and system compatibility persist. The addressing of these challenges involves the application of managerial decision support systems through the use of deep learning as a model of data predictive analytics and blockchain technology for the data management systems in operation to guarantee the immutability and transparency of data.