Description
Artificial Intelligence is transitioning from passive predictive models to Agentic AI systems capable of autonomous reasoning, goal-directed behavior, and dynamic interaction with complex environments. This book provides a comprehensive examination of this paradigm, integrating conceptual foundations with architectural frameworks and diverse real-world applications. It clarifies key definitions of agency, critically analyzes agent capabilities and limitations, and details the core mechanics of autonomous reasoning that distinguish agentic systems from traditional automation.
The book surveys emerging methodologies, including the evolution from Retrieval-Augmented Generation (RAG) to Agentic RAG, multimodal curiosity mechanisms in language models, and hybrid LLM optimizer approaches for complex scheduling and orchestration. It further bridges theory and practice through domain-specific chapters addressing deployment in healthcare emphasizing explainable interpretation for EEG-based classification enterprise BPM and workflow-centric systems, and cyber-physical infrastructures. Technical contributions also examine tool-based multi-agent engineering workflows, such as automated CAD-to-mesh transformation. Concluding with a critical assessment of challenges and opportunities, the volume offers a rigorous reference for researchers and practitioners advancing autonomous intelligent systems.
Chapter 1. The Path Ahead for Agentic AI: Challenges and Opportunities.- Chapter 2. AI Agents Explained: Definitions, Capabilities, and Limitations.- Chapter 3. Architectures and Frameworks for Agentic AI.- Chapter 4. Agentic AI: The Architecture of Autonomous Reasoning.- Chapter 5. Agentic Artificial Intelligence in Healthcare Systems: Architectures, Applications, and Challenges.- Chapter 6. Explainable AI-Enhanced Interpretation for Classification in Healthcare using EEG Signal.- Chapter 7. Agentic AI in BPM and Workflow-Centric Enterprises: A Survey of Frameworks and Deployment Best Practices.- Chapter 8. From RAG to Agentic RAG: Towards Autonomous Knowledge-Augmented AI Systems.- Chapter 9. ACMS: A Multi-Agent Architecture for Automated CAD-to-Mesh Transformation using Tool-Based Reasoning.- Chapter 10. Chain of Questions: Guiding Multimodal Curiosity in Language Models.- Chapter 11. Agentic Orchestrators for Scheduling: Hybrid LLM Optimizer Agents in Cyber-Physical Systems.
Prof. Wadii Boulila received his B.Sc. degree (First-Class Honours with Distinction) in Computer Science from the Aviation School of Borj El Amri in 2005, his M.Sc. degree in Computer Science from the National School of Computer Science (ENSI) at the University of Manouba, Tunisia, in 2007, and his Ph.D. in Computer Science through a joint program between ENSI and Télécom Bretagne, University of Rennes 1, France, in 2012. He is currently a Professor of Computer Science and the director of the RIOTU Laboratory at Prince Sultan University, Saudi Arabia. In addition, he serves as a Senior Researcher with the RIADI Laboratory at the University of Manouba and previously held the position of Senior Research Fellow with the ITI Department at the University of Rennes 1, France. Prof. Boulila has been the recipient of several prestigious awards, including the Best Young Researcher in Computer Science Award in 2021 from Beit El-Hikma, the Best Researcher Award from the University of Manouba in 2021, the Most Cited Researcher Award from the University of Manouba in 2022, and the Research Excellence Award as well as the Best Faculty Member for Most Impactful Research Output Award from Prince Sultan University. He has actively contributed to numerous research and industrial projects, with primary research interests spanning data science, computer vision, big data analytics, deep learning, cybersecurity, artificial intelligence, and uncertainty modeling. Prof. Boulila has served as a chair, reviewer, and technical program committee (TPC) member for many leading international conferences and journals. His work has garnered global recognition, and he has been named among the top 2% of scientists worldwide in his field by Stanford University. He is a Senior Member of IEEE, a Member of ACM and AAAI, and a Senior Fellow of the Higher Education Academy (SFHEA) in the U.K.
Prof. Adel Ammar received an Engineer degree from the Ecole des Mines de Nancy, France, in 2003, a Master's degree from the University of Versailles St-Quentin-en-Yvelines, France, in 2005, and a Ph.D. in Applied Data Processing, from the Université Paul Sabatier, Toulouse, France, in 2008. He is currently working as a senior researcher in the Robotics and Internet of Things Laboratory, at Prince Sultan University. His research interests include machine learning, deep learning, pattern recognition, and data mining.
Dr. Mohamed Abdelkader is an Assistant Professor at Prince Sultan University (PSU) in Riyadh, Saudi Arabia. He is also the leader of the robotics team at the Robotics & Internet of Things (RIOTU) research lab at PSU, where he leads multiple research projects in UAVs, autonomous navigation, and robotic systems. Dr. Abdelkader received his Ph.D. in Mechanical Engineering from King Abdullah University of Science and Technology (KAUST) in 2018, where his research focused on real-time distributed planning in multi-robot systems. His expertise spans SLAM, AI-based GPS-denied localization, UAV control, and multi-robot coordination. Throughout his career, he has been involved in cutting-edge research and development, including UAV swarm intelligence, autonomous perching drones for inspection, and real-time motion planning. He has contributed to 10+ US patents related to innovative robotic inspection and UAV technologies. Dr. Abdelkader has also been actively involved in academic and industrial collaborations,
