aceExploring student anxiety and experience in performance-based assessments using AIvaluate: an LLM-augmented emotionally intelligent pedagogical AI conversational agent
Abstract Performance-based assessments such as oral presentations and viva voce exams are valued for their pedagogical benefits but can also be associated with heightened student anxiety, which may affect a range of learners and hinder student motivation and overall assessment experience. This study explores the potential of AIvaluate; an emotionally intelligent, LLM-augmented conversational agent, to provide a more supportive assessment environment for such learners. Using a counterbalanced quasi-experimental,…
State of the Map Kerala 2025 Pre-Event Workshop for Student SAT Kannur University 09 by Manojk. CC BY-SA 4.0 · https://creativecommons.org/licenses/by-sa/4.0
Researchers compared traditional face-to-face performance-based assessments with sessions mediated by AIvaluate, an LLM-augmented emotionally intelligent conversational agent, using 35 pre-university students in a counterbalanced within-subjects design measuring emotional state, usability and qualitative perceptions.
Lower anxiety and good usability suggest AI mediation may help learners whose anxiety exceeds their zone of optimal functioning, but uncertainty remains about learning benefits, attainment effects, and how to balance reduced social pressure against loss of human interaction and technical reliability.
- Counterbalanced quasi-experimental within-subjects design with 35 pre-university students compared traditional face-to-face PBAs with AIvaluate-mediated sessions.
- Emotional state reports, usability ratings and qualitative feedback were analyzed to evaluate anxiety, system usability and learner perceptions.
- Thematic analysis identified perceived advantages such as reduced social pressure, flexible pacing and ease of use.
Students reported significantly lower anxiety during AIvaluate-mediated performance-based assessments compared to traditional face-to-face assessments, with usability rated in the good range.
The rundown
The study tested AIvaluate, described as an emotionally intelligent, LLM-augmented conversational agent, against traditional oral presentations and viva voce exams in a within-subjects comparison.
By publication date 2026-06-02, authors reported lower anxiety in AI sessions and good usability, but also noted technical issues and less dynamic interaction, and called for research on hybrid models and long-term effects on performance and well-being.
Sources
- Peer-reviewedEducational technology research and development2026-06-02
How should this claim be treated?
The debate