This fully funded PhD position at the University of Exeter focuses on the foundations, systems, and applications of agentic AI powered by large language models (LLMs). LLMs are transforming the way agents interact with the world, enabling multi-step planning and action across diverse domains. The project aims to address key challenges in making LLM-based agents reliable, efficient, and collaborative in real-world environments, with an emphasis on correct tool use, predictable performance, and robust operation across heterogeneous infrastructures. Research themes include theoretical modelling, algorithm design and analysis, retrieval-augmented generation for up-to-date knowledge, efficient fine tuning, closed-loop improvement from user feedback, multi-agent collaboration, distributed infrastructure, and real-world applications such as air traffic control and environmental intelligence. The programme offers an inclusive research environment bridging theory and systems, mentorship from Prof. Shiqiang Wang (with extensive academic and industry experience), and secondary supervisors Dr. George De Ath and Dr. Jawad Fayaz, who bring expertise in air traffic control, environmental intelligence, machine learning, and Bayesian modelling. Students will have opportunities to publish at top AI/ML venues, collaborate with academic and industry partners, and access advanced computing resources. The studentship covers UK and international tuition fees and provides a tax-free stipend of at least £20,780 per year. Applicants should have a background in computer science or a related field, strong motivation for impactful AI research, excellent English communication skills, proficiency in programming and modern ML tools, and ideally experience with LLMs. Both UK and international candidates are encouraged to apply. The application deadline is November 30, 2025. For more information and to apply, visit the University of Exeter funding page.