Faculty of Engineering and Physical Sciences EPSRC Project Proposals 2025/26 - Large Language Model for System Software

Eligibility: UK Only

Funding: School of Computer Science studentship consisting of the award of fees, together with a tax-free maintenance grant of £20,780 per year for 3.5 years. 

Lead Supervisor’s full name & email address

Dr. Chunwei Xia: c.xia@leeds.ac.uk

Co-supervisor’s full name & email address

Professor Zheng Wang: z.wang5@leeds.ac.uk

Project summary

Large Language Models (LLMs) have profoundly transformed the way we study, work, and think. Models such as ChatGPT have the potential to free individuals from the intricate and labour-intensive processes involved in writing and coding. Developing system software, such as compilers, is an exceedingly complex task that often requires investments of hundreds of millions of dollars. This project aims to explore the extent to which LLMs can be harnessed to assist in the development of system software.

Key questions include how LLMs can support programmers in writing complex logical code, generating high-quality tests, and optimizing performance. Moreover, when integrated with reinforcement learning, LLMs can iteratively improve by learning from feedback. If successful, this approach could present a ground-breaking solution for system software development.

The candidate in this role will be expected to engage deeply with the interdisciplinary domains of LLMs, software engineering, and performance optimization, to advance the next frontier of cutting-edge AI in system software.

Please state your entry requirements plus any necessary or desired background

A first class or an upper second class British Bachelors Honours degree (or equivalent) in an appropriate discipline.

Advert information