Only the interactive antagonistic agent, not stepwise guidance, significantly shifted novice designers' design thinking relative to self-reflection¶

Claim · All claims
Evidence · 1 study · causal r2 · q3 · i3 large
Currency · newest study 2026 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q3 i3 On the item asking whether the activity changed design thinking, the Interactive Engagement group scored significantly higher than Self Reflection (g = 1.30), while the Stepwise Guidance contrast was not significant. → Howard Ziyu Han 2026

Evidence¶

Howard Ziyu Han 2026¶

Howard Ziyu Han, Nikolas Martelaro. (2026). Enacting Constructive Conflicts with AI Agents to Enhance Reconsideration among Novice Interaction Designers. https://arxiv.org/abs/2608.04166 doi:10.48550/arxiv.2608.04166

q3 · i3 · causal · r2

Post-survey contrast in the 45-participant between-subjects experiment: the agent condition exceeded Self Reflection with g = 1.30, a large effect, while the Stepwise Guidance contrast was not significant (padj = .085, g = 0.38).

"with the Interactive Engagement group (𝑀= 5.33,𝑆𝐷= 1.35) significantly higher than Self Reflection ( 𝑀= 3.60,𝑆𝐷= 1.24;𝑝𝑎𝑑 𝑗 =. 003, 𝑔= 1.30, large effect). The Stepwise Guidance–Self Reflection con- trast was not significant (𝑀= 4.13,𝑆𝐷= 1.46;𝑝𝑎𝑑 𝑗 =. 085,𝑔= 0.38, small-to-medium effect)."

Discussion¶

Related Claims¶

• Reflective Practice Improves Outcomes When Structured — the general claim this finding bears on, with the studies behind it

• Conflict-based instruction improves science conceptual learning, though staged contradictions helped only learners who reported being confused, and no study isolates disequilibrium as the mechanism — the general claim this finding bears on, with the studies behind it

• Minimal guidance is less effective for novices than explicit instruction — the general claim this finding bears on, with the studies behind it

• Both stepwise constructive-conflict guidance and the antagonistic agent led novice designers to reconsider what makes a design effective more than unsupported self-reflection — related
• Stepwise constructive-conflict guidance reduced new idea generation, while the antagonistic agent played a more balanced role — related
• The antagonistic agent surfaced a broader set of stakeholder concerns than novice designers reached on their own — related
• Both constructive-conflict conditions produced substantially more idea editing between design iterations than unsupported self-reflection — related
• Novice designers deleted ideas only when confronted with stakeholder friction; unsupported self-reflection produced no deletions — related
• Reflection interventions in higher education have a medium positive average effect on learning that varies with duration, peer interaction and the reflective activity used — a broader claim this one bears on