Mindful-condition students rated the pedagogical agent as more supportive and more concerned about their well-being on single items¶

Claim · All claims
Evidence · 1 study (2 entries) · causal r1–r2 · q3
Currency · newest study 2026 · not yet checked against its sources · not reviewed by a person

In Rief et al. (2026), seventh graders practised algebra in the "Math with Matt" tutoring system. The Mindful version added an LLM-based mindful chat, in which the pedagogical agent Matt gave context-sensitive emotional support, and mindful (not only evaluative) feedback and hint messages; the Cognitive version gave cognitive support only.

Subclaims¶

q3 i? The item 'I feel supported by Matt' was rated significantly higher in the Mindful condition. → Rief 2026 q3 i? The item 'I believe that Matt is very concerned about my well-being' was rated significantly higher in the Mindful condition. → Rief 2026 (2)

Evidence¶

Rief 2026¶

Rief, V., Hladký, M., Yoo, M., Heel, S., Sato, S., Nagashima, T. (2026). Beyond Problem Solving: Large Language Models for Emotional and Reflective Support in Mathematics Learning. https://arxiv.org/abs/2609.02611 doi:10.48550/arxiv.2609.02611

q3 · i? · causal · r1

Single-item analyses of the self-composed pedagogical-agent questionnaires (Cronbach's alpha 0.88-0.94) in the 42-student experiment: the socio-emotional support item was significantly higher in the Mindful condition (W=167.0, p=.028); no effect size was printed.

"revealing that the item "I feel supported by Matt" (socio-emotional support questionnaire) was significantly higher rated in the Mindful condition (W=167.0, p=.028)"

Rief 2026 (2)¶

Rief, V., Hladký, M., Yoo, M., Heel, S., Sato, S., Nagashima, T. (2026). Beyond Problem Solving: Large Language Models for Emotional and Reflective Support in Mathematics Learning. https://arxiv.org/abs/2609.02611. doi:10.48550/arxiv.2609.02611

q3 · i? · causal · r2

The warmth questionnaire item about concern for well-being was also rated significantly higher in the Mindful condition (W=139.5, p=.046) in the same single-item analysis; no effect size was printed.

"as well as the item “I believe that Matt is very concerned about my well-being” (warmth questionnaire) (W=139.5,p=.046)."

Discussion¶

Related Claims¶

• Students' beliefs about the cognitive, motivational and affective dimensions of their teacher's functioning load on a single factor — related
• Adding a second writing agent increased reported cognitive load, and writing confidence did not increase monotonically with support, with the Single condition reporting the lowest confidence — related
• The mindfulness interventions did not significantly change anticipatory or executive state-MA relative to cognitive support alone — related