Both constructive-conflict conditions produced substantially more idea editing between design iterations than unsupported self-reflection¶

Claim · All claims
Evidence · 1 study · causal r2 · q3
Currency · newest study 2026 · checked against its sources 2026-10-20 (automated, 1 of 1 entry) · not reviewed by a person

Subclaims¶

q3 i? Stepwise Guidance participants primarily made enhancements, whereas Interactive Engagement participants made both revisions and enhancements. → 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 · i? · causal · r2

Sub-analysis of edit types in the same experiment: revisions were significantly higher only in the agent condition, suggesting the Stepwise Guidance group primarily engaged in enhancements.

"Revisions were significantly higher in the Interactive Engagement group than in the Self Reflection (𝑝𝑎𝑑 𝑗 =. 023), with no difference between Stepwise Guidance and Self Reflection."

Discussion¶

Related Claims¶

• Diagnostic Review revisions contained larger shares of meaning-change, organization, and content/argument work, while Control revisions remained more dependent on surface-level editing — the general claim this finding bears on, with the studies behind it

• 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

• Only the interactive antagonistic agent, not stepwise guidance, significantly shifted novice designers' design thinking relative to self-reflection — related
• The antagonistic agent surfaced a broader set of stakeholder concerns than novice designers reached on their own — 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
• Stepwise constructive-conflict guidance reduced new idea generation, while the antagonistic agent played a more balanced role — related
• Novice designers deleted ideas only when confronted with stakeholder friction; unsupported self-reflection produced no deletions — related
• Perturbation type determines the interaction types needed: conflicting evidence elicits argumentation — related