A secondary ENA adding ICAP engagement codes showed proactive interactions linked constructive engagement with adequate reasoning, while reactive dialogues emphasised procedural pairings¶

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

Subclaims¶

q2 i? In the secondary ENA with epistemic and engagement codes, proactive interactions showed stronger I-CON–EP-CP-Adeq and EP-PS–I-CON links; reactive dialogues emphasised EP-OFF–I-ACT and EP-PS–I-ACT pairings. → Yueqiao Jin 2025

Evidence¶

Yueqiao Jin 2025¶

Yueqiao Jin, Kaixun Yang, Roberto Martinez-Maldonado, Dragan Gašević and Lixiang Yan. (2025). The Agency Gap in AI-Supported Writing: How Reactive and Proactive Agent Designs Shape Multimodal Reasoning. https://arxiv.org/abs/2507.04398 doi:10.48550/arxiv.2507.04398

q2 · i? · causal · r2

Secondary ENA including ICAP engagement codes for 244 learner utterances explained 27.5% (MR1) and 26.4% (SVD2) of variance; conditions again differed along MR1 (W=96, p<.001, Cliff's δ=−0.78, large), with the quoted edge-weight contrasts.

"Proactive interactions showedstrongerlinksbetweenconstructiveengagementandadequatereasoning(I-CON–EP-CP-Adeq,𝑤=−0.13)and betweenfactualandconstructivecontributions(EP-PS–I-CON,𝑤=−0.13)."

Discussion¶

Related Claims¶

• Scaffolded assistant support marks richer constructive participation at the conversation level across all six task settings — the general claim this finding bears on, with the studies behind it
• Proactive AI agent dialogues showed stronger conceptual–adequate reasoning links while reactive dialogues showed stronger factual/off-task associations — possibly the same claim (merge candidate)
• Cluster analysis of student-AI dialogue identifies three distinct collaboration profiles: Delegated Reasoning, Concerted Interpretation, and Delegated Elaboration — related
• Epistemic network analysis shows metacognitive behaviors co-occur with invitation actions in DR and DE but with human-initiated reasoning and elaboration in CI — related
• Interactive engagement requires both partners' utterances to be primarily constructive and a sufficient degree of turn taking — related
• In observed Australian secondary classrooms, only a minority of lesson tasks stimulated Constructive or Interactive engagement — related
• Using generative AI as a dialogic partner for brainstorming, feedback, and co-construction can support constructive and interactive learning — related
• Quality control in peer assessment can be exercised proactively or reactively on students and their assessments — related
• Only 11.1% of interactions pair mastery-oriented aims with advanced strategies such as epistemic justification — related
• Reactive FOF is more time-consuming than proactive FOF, reducing opportunities to elaborate on preselected grammar points — related
• Experts respond to classroom events predictively and proactively via precursor detection, while novices are either unaware or reactively aware — related