This project investigates the development of an AI system for assessment within experiential, project-based learning environments. The system will leverage modern AI architectures to support learning activities and tasks and assess them. Emphasis will be placed on modelling core computing knowledge, and evaluation beyond traditional assessments. Key research challenges include designing reliable evaluation mechanisms, ensuring fairness and consistency, and supporting meaningful human–AI interaction. The outcomes aim to advance scalable, AI-driven assessment frameworks applicable to education and other experiential learning contexts.
School
Computer Science and Engineering
Research Area
Artificial intelligence | Natural language processing | Deep learning | AI agents | Software engineering | Web development | Human-computer interaction
Suitable for recognition of Work Integrated Learning (industrial training)?
Yes
- Research environment
- Expected outcomes
- Supervisory team
- Reference material/links
Interns will work closely with academic supervisors and research staff, with access to environment that support open research, regular technical discussions, and engagement with ongoing projects in modern AI frameworks and it's application. Interns will also gain hands-on experience in designing, implementing, and evaluating advanced AI systems, while contributing to research outcomes with potential for publication in leading venues.
- Working prototype of an agentic AI system
- Research report including review of existing work, method, evaluation of proposed solution
- Source code and technical documentation
- To be discussed with selected interns.