Stepwise constructive-conflict guidance reduced new idea generation, while the antagonistic agent played a more balanced role¶

Claim · All claims
Evidence · 1 study (2 entries) · causal r2 · q3 · i3 large
Currency · newest study 2026 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q3 i3 Stepwise Guidance participants added significantly fewer new ideas in the second iteration than Self Reflection participants (g = −1.03). → Howard Ziyu Han 2026 q3 i? The Interactive Engagement condition fell between the two, with neither contrast significant after Bonferroni correction. → Howard Ziyu Han 2026 (2)

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

Kruskal–Wallis on ideas added in the second iteration (H(2) = 9.12, p = .010, ε² = .21): Stepwise Guidance participants added significantly fewer ideas than Self Reflection, Hedges' g = −1.03, a large effect.

"Post-hoc tests showed that participants in the Stepwise Guidance condition (𝑀= 0.80, SD= 1.15) added significantly fewer ideas than those in the Self Reflection condition (𝑀= 2.13,𝑆𝐷= 1.36;𝑝𝑎𝑑 𝑗 =. 008, Hedges’ g=− 1.03, large effect)."

Howard Ziyu Han 2026 (2)¶

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

q3 · i? · causal · r2

Same idea-addition analysis: the agent condition's mean fell between the other groups and neither pairwise contrast survived Bonferroni correction.

"The Interactive Engagement condition (𝑀= 1.27,𝑆𝐷= 0.80) fell between the two. Neither contrast was significant after Bonferroni correction (vs. Self Reflection,𝑝𝑎𝑑 𝑗 = .446; vs. Stepwise Guidance,𝑝 𝑎𝑑 𝑗 =.346)."

Discussion¶

Related Claims¶

• 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
• Only the interactive antagonistic agent, not stepwise guidance, significantly shifted novice designers' design thinking relative to self-reflection — related
• Both constructive-conflict conditions produced substantially more idea editing between design iterations than unsupported self-reflection — related
• 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
• Novice designers deleted ideas only when confronted with stakeholder friction; unsupported self-reflection produced no deletions — related
• The antagonistic agent surfaced a broader set of stakeholder concerns than novice designers reached on their own — related