Citation :

Muhammad Shahbaz, Muhammad Emran, Rubiya Hanni Shafiulla Kannavalli, Farhan Ajmal Khan, Meer Zafarullah Noohani, "Toward AI-Augmented Applied Systems: Emerging AI and LLM Directions Across Trajectory Prediction, Cybersecurity, and Engineering Automation," International Journal of Computer & Organization Trends (IJCOT), vol. 16, no. 3, pp. 9-15, 2026. Crossref, https://doi.org/10.14445/22492593/IJCOT-V16I3P302

Abstract

This paper reviews fifteen recent publications (2015-2026) spanning trajectory prediction, cybersecurity and trust management, classical machine learning and algorithmic optimisation, and engineering automation, and asks a forward-looking question: where is artificial intelligence — particularly Large Language Models (LLMs), foundation models, and agentic AI systems — positioned to extend each of these research directions next? For each of four thematic clusters we first summarise the current method documented in the reviewed sources, then discuss a concrete, currently-emerging AI direction grounded in recent (2025-2026) literature: LLM- and foundation-model-based trajectory reasoning for Cluster A; agentic, LLM-driven security-operations copilots for Cluster B, including a reported 6.5x improvement in malicious-alert identification over human analysts in one production deployment; learned and graph-neural-network-based approaches to the classical optimisation and graph-isomorphism problems in Cluster C; and natural-language-to-workflow agentic automation for the low-code and embedded-systems work in Cluster D. Throughout, we explicitly separate what the reviewed papers themselves established from this review's own forward-looking analysis, and close with a discussion of the reliability, interpretability, and adversarial-robustness risks that accompany each proposed direction.

Keywords

Large Language Models, Agentic AI, Foundation Models, Trajectory Prediction, Cybersecurity, Trust Management, Graph Neural Networks, Engineering Automation.

References

[1] Zain Ul Abideen et al., “Improved Deep Learning-based Approach for Spatial-temporal Trajectory Planning Via Predictive Modeling of Future Location,” KSII Transactions on Internet and Information Systems, vol. 18, no. 7, pp. 1726-1748, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[2] Zain Ul Abideen et al., “Advancing Pedestrian Trajectory Prediction with Interaction-Aware 3D-Dual Contextualized Modeling,” Egyptian Informatics Journal, vol. 31, pp. 1-17, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[3] Syed Talha Hussain et al., “Securing the Bot Eco System: IAM Framework for RPA and AI BOTS,” 2026 IEEE 5^th International Conference on Computing and Machine Intelligence (ICMI), pp. 1-9, 2026.
[CrossRef] [Google Scholar] [Publisher Link]

[4] Han Chang et al., “Two-Round Optimization Algorithm based on Quadric Error Metrics,” IEEE Access, vol. 13, pp. 30021-30035, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[5] Muhammad Shahbaz et al., “Deployment of Honeypot System for Threat Detection and Intelligence in Modern Cybersecurity Architectures,” 2026 1^st International Conference on Innovations in Information and Communication Technology (IICT), Jamshoro, Pakistan, pp. 1-5, 2026.
[CrossRef] [Google Scholar] [Publisher Link]

[6] Muhammad Haleem Junejo, Muhammad Shahbaz, and Muhammad Emran, “Trust-based Management for Internet of Vehicles Via Wireless Sensor networks: Safeguarding Trust During Journeys,” 2026 IEEE 5^th International Conference on Computing and Machine Intelligence (ICMI), Al-Ahsa, Saudi Arabia, 2026.
[CrossRef] [Google Scholar] [Publisher Link]

[7] Nisar Ahmed et al., “Face Recognition Comparative Analysis using Different Machine Learning Approaches,” Advances in Science and Technology Research Journal, vol. 15, no. 1, pp. 265-272, 2021.
[CrossRef] [Google Scholar] [Publisher Link]

[8] Abdul Mujeeb et al., “Electronic Toll Collector Framework,” Advances in Science and Technology Research Journal, vol. 16, no. 1, pp. 294-302, 2022.
[CrossRef] [Google Scholar] [Publisher Link]

[9] Nisar Ahmed et al., “A Software Capable of simulating Peer-to-Peer Energy Trading,” International Journal of Applied Physical Sciences, vol. 7, pp. 18-26, 2021.
[CrossRef] [Google Scholar] [Publisher Link]

[10] Hafiz Shafiq Ur Rehman Khalil, Nisar Ahmed, and Yijun Yang, “Mouse Pointing Endpoint Prediction to Distinguish between Human and Bot using Kinematic Template Matching,” International Conference on Human-Computer Interaction, Montreal, QC, Canada, pp. 343-364, 2026.
[CrossRef] [Google Scholar] [Publisher Link]

[11] Ahcene Bounceur et al., “Privacy-Preserving Multiclass Intrusion Detection in In-vehicle CAN Networks using Federated Learning,” Scientific Reports, 1-53, 2026.
[CrossRef] [Google Scholar] [Publisher Link]

[12] Nisar Ahmed et al., “The Synergy of Low-code/No-code and AI/ML: Enhancing Intelligent Automation,” World Journal of Engineering and Technology, vol. 13, no. 4, pp. 754-763, 2025.
[Google Scholar]

[13] Nisar Ahmed et al., “How to Protecting Kernal Code and Data,” International Journal of Computer and Organization Trends (IJCOT), vol. 5, no. 4, pp. 20-23, 2015.
[CrossRef] [Publisher Link]

[14] Nisar Ahmed, “Understanding Real Time OS Concepts,” International Journal of Scientific and Engineering Journal, vol. 6, no. 9, pp. 1-6, 2015.
[Google Scholar]

[15] Utku Cem Sankal et al., “Target Cell Selection Algorithms in Graph Isomorphism Problem,” International Journal of Scientific and Technical Research in Engineering (IJSTRE), vol. 6, no. 4, pp. 35-47, 2021.
[Google Scholar] [Publisher Link]

[16] Wei Dai et al., “Large Foundation Models for Trajectory Prediction in Autonomous Driving: A Comprehensive Survey,” arXiv Preprint, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[17] Scott Freitas, and Amir Gharib, “GenAI-Driven Threat Detection with Microsoft Security Copilot,” arXiv Preprint, pp. 1-8, 2026.
[CrossRef] [Google Scholar] [Publisher Link]

[18] Keyulu Xu et al., “How Powerful are Graph Neural Networks?,” arXiv preprint, pp. 1-17, 2019.
[CrossRef] [Google Scholar] [Publisher Link]

[19] Falak Ali, “Real-Time Decision Processing in Artificial Intelligence Systems: A Survey of Scheduling, Inference, and Security Foundations,” International Journal of Emerging Trends in Engineering and Development (IJETED), vol. 16, no. 5, pp. 1-4, 2026.
[CrossRef] [Google Scholar] [Publisher Link]

[20] Falak Ali, “Divide-and-Conquer Decomposition Strategies for Real-Time Artificial Intelligence Decision Systems: A Comparative Survey,” International Journal of Emerging Trends in Engineering and Development (IJETED), vol. 16, no. 5, pp. 1-6, 2026.
[CrossRef] [Google Scholar] [Publisher Link]