About the Project
A fully funded PhD opportunity to participate in the world-leading research undertaken by the EPSRC Doctoral Landscape Award at the University of Sheffield.
Supervised by Dr Zheng Yuan and Dr Bei Peng.
The University of Sheffield is one of the leading Russell Group universities in the UK. We carry out cutting-edge research with strong links to industry. When you enrol to do a PhD with us, you will be working with world-leading academics and have access to top of the range facilities. As a PhD student you will have the opportunity to gain skills not only to conduct research, but also to take your career to the next level, whether you want to stay in academia, go into industry or the public sector, or set up your own company. You will have access to a range of training and support services to help you excel in your studies and beyond.
Project Description
Artificial intelligence (AI) tools are increasingly being used in education, particularly for writing and language learning. Many of today’s systems act as a single assistant—offering corrections, generating ideas, or providing feedback from one fixed perspective. While this “one user–one AI” model is convenient, it overlooks a key feature of how people actually learn: interaction with others. In classrooms, progress often happens through discussion, debate, and collaboration, when different voices challenge, support, and inspire one another.
This PhD project explores how multi-agent AI systems can better reflect these human learning dynamics. Instead of relying on a single AI helper, learners would interact with a team of AI personas that take on complementary roles—for example, a facilitator who helps structure ideas, a challenger who asks critical questions, and a supporter who provides examples or encouragement. Working together, these agents can help students think more deeply, generate creative ideas, and improve their writing over time.
The research will combine technical development with human-centred evaluation. The student will design and build a prototype that allows learners to collaborate with multiple AI agents through interactive writing and feedback sessions. The project will also investigate how learners perceive trust, fairness, and usefulness when receiving input from several AI voices, compared with feedback from a single system.
The project will be supervised within the School of Computer Science at the University of Sheffield, with additional support and collaboration from the School of Education. This cross-faculty partnership will ensure that the research is grounded in both technical innovation and pedagogical relevance. The PhD researcher will develop interdisciplinary expertise spanning AI model design, dialogue systems, user-experience evaluation, and educational research, particularly in the context of language and writing education.
Working at the intersection of computer science, linguistics, and learning sciences, the student will gain experience not only in building and testing AI systems but also in understanding how such technologies can meaningfully support learning in authentic educational settings. The collaboration with the School of Education will offer opportunities for joint supervision, access to expertise in learning design and assessment, and engagement with teacher education and language learning communities. Together, these experiences will enable the researcher to develop a comprehensive understanding of both the technical and human dimensions of AI for Education (AI4Ed).
Beyond the immediate technical goals, the project addresses broader questions about the future of learning in an AI-enabled world. How can AI systems encourage rather than replace critical thinking? How can multiple AI “voices” make feedback more balanced, transparent, and inclusive? And how can technology be designed to support diverse learners in equitable ways?
By reimagining AI not as a solitary assistant but as a collaborative partner, this project aims to contribute to the next generation of educational technologies—tools that help learners think together with AI, rather than simply receive answers from it. The findings could inform future systems for writing instruction, group learning, and creative collaboration, benefiting educators, learners, and designers of responsible AI systems alike.
How to apply
Interested candidates are strongly encouraged to contact the project supervisors to discuss your interest in and suitability for the project prior to submitting your application.
Please refer to the EPSRC DLA webpage for detailed information about the EPSRC DLA and how to apply.
Applicants must ensure that they use the correct application form linked to the EPSRC DLA webpage and must submit an application for October 2027 entry. The form is unique to the EPSRC DLA. It contains the list of advertised projects from which to select, and three questions specific to the DLA.
The application deadline is 17:00 GMT 13 January 2027.
The majority of our DLA studentships will be allocated to candidates who qualify for Home fee status, in accordance with EPSRC funding regulations which place strict limits on international recruitment.
Funding Notes
The award will fund the full tuition fee and a maintenance stipend at the UKRI rate (currently £21,805 per annum) for 3.5 years, as well as a research grant to support costs associated with the project.
