PhD Studentship: QoE-Driven Agentic AI for Automated Bug Discovery in Video Games (Collaborative Doctorate with Sony Interactive Entertainment) University of Surrey in United Kingdom

[Fully and directly funded for this project only. Home or International fees for 42 months. UKRI standard stipend £21,805 per annum for 42 months (academic year 2026/27). RTSG: £1,500 per year. Additional conference funding (up to £3,000) may be available, subject to approval.]

This PhD studentship at the University of Surrey, in collaboration with Sony Interactive Entertainment (SIE), offers a unique opportunity to advance automated bug discovery in video games using agentic AI and Quality of Experience (QoE) models. The project addresses the challenge of validating complex, continuously updated games at scale, where manual QA is insufficient and automated methods often lack clarity and prioritisation by player impact.

The research will develop a multi-agent AI framework with three roles: Explorer (actively probes games to discover failures), Inspector (verifies and reproduces issues, capturing minimal but sufficient evidence), and Reporter (produces structured bug reports for triage). A key innovation is the explicit QoE severity model, which ranks bugs based on predicted player impact—such as frustration, immersion disruption, fairness, comfort, or usability—using human feedback and QA expertise. The project will evaluate improvements over scripted and random baselines using metrics like unique bugs per hour, reproducibility rate, evidence quality, and correlation between severity ranking and human judgement.

The studentship is fully and directly funded for 42 months, covering home or international fees, a UKRI standard stipend (£21,805 per annum), RTSG (£1,500 per year), and potential conference funding (up to £3,000). The student will benefit from SIE co-supervision, industry-informed glitch taxonomies, and reporting requirements, with appropriate data, IP, and publication governance. The work aligns with Surrey’s GAIN programme and SAHCI games provision, supporting standards-oriented impact through engagement with ITU-T gaming QoE initiatives.

Applicants should have strong programming skills (preferably Python), experience in machine learning/AI or software engineering for interactive systems, and ideally game development or design experience with platforms like Unity, Unreal, or Godot. Up-to-date knowledge of generative AI, vision-language models, and agent-based AI systems is desirable. The ability to design and conduct human-centred evaluation experiments, excellent communication skills, and effective collaboration with industry partners under confidentiality constraints are expected. The position is open to UK and international candidates, starting October 2026.

To apply, discuss your project with a prospective supervisor and submit your application via the Innovative Media Technology PhD programme page. In place of a research proposal, upload a document stating the project title and the relevant supervisor’s name. The application deadline is 30 May 2026. For enquiries, contact Dr Femi Adeyemi-Ejeye.