High prior knowledge students sent significantly more messages and generated denser multi-turn interaction with AI agents than low prior knowledge students¶

Claim · All claims
Evidence · 1 study · associational r2 · q2
Currency · newest study 2025 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q2 i? The high prior knowledge group sent more messages (M = 35.76, SD = 46.74) than the low group (M = 14.47, SD = 23.84), z = -2.750, p = .006, and engaged in significantly more multi-turn conversations, z = -2.83, p = .005. → Hao 2025

Evidence¶

Hao 2025¶

Hao, Z.; Cao, J.; Li, R.; Yu, J.; Liu, Z.; Zhang, Y. (2025). Mapping Student-AI Interaction Dynamics in Multi-Agent Learning Environments: Supporting Personalised Learning and Reducing Performance Gaps. https://osf.io/preprints/eduRxiv

q2 · i? · associational · r2

Group comparison of dialogue volume in the MAIC course. The article also reports more AI-peer responses in the high group (M = 80.06 vs. 30, z = -3.033, p = .002) and more AI-teacher responses (M = 54.82 vs. 27.32, z = -2.866, p = .004).

"The average number of messages sent by the high prior knowledge group (M = 35.76, SD = 46.74) was significantly higher than the low prior knowledge group (M = 14.47, SD =23.84), z = -2.750, p =.006"

Discussion¶

Related Claims¶

• Students with low prior knowledge achieved the greatest learning gains in the multi-agent AI course, with a significant main effect of prior knowledge on gain — related
• High prior knowledge students engaged more in co-regulation behaviors while low prior knowledge students relied more on question-raising and idea-confirming sequences — related