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¶
Claim · All claims
Evidence · 1 study · associationalr1·q2·i3large
Currency · newest study 2025 · not yet checked against its sources · not reviewed by a person
Subclaims¶
Reading the evidence codes
q is the design tier, i the impact, n the sample, and the kind with its r
the rigour judged within that kind: what each code means.
This claim: no standardized effect is recorded in observations/ for it yet, so no benchmark reading is possible.
q2 i3 A one-way ANOVA on learning gains showed a significant main effect of prior knowledge level, F(2, 69) = 22.95, p < .001, partial η² = .400, with the low prior knowledge group gaining most (M = 1.88) and the high group showing a loss (M = –1.09). → 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 · i3 · associational · r1
One-way ANOVA comparing learning gains across three prior-knowledge groups (top/bottom 30% plus medium) in the MAIC course. The article reports "partial η² = .400" and group means of 1.88, 0.36, and –1.09 for low, medium, and high groups.
"The results revealed a significant main effect of prior knowledge level on learning gain, F(2, 69) = 22.95, p < .001, partial η² = .400. Students in the low prior knowledge group achieved the greatest learning gains (M = 1.88, SD = 1.36), followed by the medium group (M = 0.36, SD = 1.34), while the high group experienced a learning loss (M = –1.09, SD = 1.37)"
Discussion¶
Learner Variables¶
- Prior Knowledge — predictor: learners who differ on it differ in outcomes
Related Claims¶
- High prior knowledge students sent significantly more messages and generated denser multi-turn interaction with AI agents than low prior knowledge students — related
- Prior knowledge significantly predicted algebra posttest scores and learning gains, with high-prior-knowledge students scoring higher and low-prior-knowledge students gaining more — related
- Agent-condition learning gains trended higher (marginal), with Agent LPK students gaining significantly more than Non-Agent HPK students — related
- Students with low prior knowledge show significantly higher proportional learning gains than students with high prior knowledge when learning with MetaTutor — related
Page metadata
| Field | Value |
|---|---|
status |
review |
generated |
by process:wiki-ingest on 2026-10-29 |
trust |
unverified — no one has confirmed this page's content |
Frontmatter is the page's machine-readable record — see the Schema & Guide.