This track investigates how generative AI can support the design, execution, and evaluation of assessments within intelligent tutoring systems. Topics include automated item generation, adaptive testing, rubric creation, feedback generation, competency diagnosis, and the assessment of open-ended responses. Contributions may explore multimodal assessment, simulation-based tasks, authentic evaluation, and continuous formative assessment. The track also welcomes methods for validating AI-generated assessment materials and detecting unreliable or biased judgements. Particular importance is given to validity, reliability, transparency, fairness, and human oversight.

Focus: Generative AI methods for creating and delivering adaptive assessments and interpreting learner performance within ITS. Emphasis is placed on trustworthy assessment practices that produce valid feedback and support learning progression.