Student–AI interaction: unveiling the impact of AI agents on vocabulary learning – A meta-analysis

Abstract The rapid proliferation of artificial intelligence (AI)-driven educational interventions has generated substantial interest in their effectiveness for vocabulary acquisition; however, the existing literature presents inconsistent findings. This meta-analysis, drawing on 28 studies and integrating 55 effect sizes via a three-level random effects model, demonstrates a significant overall positive effect of AI agents on vocabulary learning (effect size = 0.904, 95 % CI: 0.724, 1.084, p < 0.0001). Furthermore, moderator analysis identified significant moderating effects of both AI embodiment ( F (1, 53) = 7.446, p < 0.01) and intervention duration ( F (20, 24) = 5.563, p < 0.001). Grounded in the student–AI interaction framework, this meta-analysis provides a theory-informed synthesis of how AI-supported instructional designs relate to vocabulary learning outcomes.