PhD Studentship: LLM-Based Agentic AI – Foundations, Systems & Applications (University Funded)
[UK and International tuition fees covered plus annual tax-free stipend of at least £20,780 per year.] This PhD studentship at the University of Exeter focuses on the foundations, systems, and applications of LLM-based agentic AI. Large language models (LLMs) are revolutionizing how agents can read, write, call tools, and follow instructions, enabling multi-step planning and action in diverse domains. The project aims to address the challenge of making LLM-based agents reliable, efficient, and collaborative in real-world environments, ensuring correct tool use, predictable cost and speed, and robust performance across heterogeneous infrastructures and devices. Research themes include the foundations of LLM-based agents, enabling technologies for agents, multi-agent collaboration and coordination, agentic systems and distributed infrastructure, and practical applications of agentic AI. Students will benefit from an inclusive research environment that bridges theory and system building, with opportunities to publish at top AI/ML venues and validate ideas on real platforms. Mentorship will be provided by Prof. Shiqiang Wang, who brings nearly a decade of industry experience from the United States, and secondary supervisors Dr. George De Ath and Dr. Jawad Fayaz, experts in air traffic control, environmental intelligence, machine learning, uncertainty quantification, and Bayesian modelling. The programme offers access to advanced computing resources and opportunities to collaborate with academic and industry partners. 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. The studentship covers UK and international tuition fees and provides a tax-free stipend of at least £20,780 per year. Both UK and international candidates are encouraged to apply, with selection based on merit. The application deadline is November 30, 2025.