Attempt-reduction patterns differed across course parts: Diagnostic and General Feedback were associated with fewer attempts for New Content, Single-Issue for Old Content¶

Claim · All claims
Evidence · 1 study · causal r2 · q2
Currency · newest study 2026 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q2 i? For New Content, Diagnostic Feedback and General Feedback were associated with fewer attempts; for Old Content, Single-Issue Feedback was associated with fewer attempts; no significant attempt difference between parts appeared in the No Feedback condition. → Tsvetomila Mihaylova 2026

Evidence¶

Tsvetomila Mihaylova 2026¶

Tsvetomila Mihaylova, Evanfiya Logacheva, Arto Hellas, Jing Fan, Francisco Castro, Bita Akram, Narges Norouzi, Peter Brusilovsky, Juho Leinonen. (2026). The Effects of Structured LLM-Generated Feedback on Programming Assignment Performance. https://arxiv.org/abs/2605.16933 doi:10.48550/arxiv.2605.16933

q2 · i? · causal · r2

NB-GLMM on attempts with hint type × course part interaction (Table 3). Single-Issue × Old Content β=−0.131 (HDI [−0.248, −0.018]); General × Old Content β=−0.107 (HDI including zero). Unlike time to success, no significant between-part difference appeared without feedback.

"For the New Content , again the Diagnostic Feedback is associated with fewer attempts, but interestingly, the General Feedback , which also hints to solution, shows a reduced number of attempts. For the Old Content , the Single-Issue Feedback is associated with fewer Attempts to Success."

Discussion¶

Related Claims¶

• Advanced students showed reduced attempts with all hint types, while novices did not clearly benefit and made slightly more submissions with Single-Issue Feedback — related
• All three LLM feedback types credibly reduced attempts to success relative to the baseline, with the largest reduction for Diagnostic Feedback — a broader claim this one bears on
• Feedback effectiveness varied by content recency: guidance-heavy feedback performed less consistently on newer material released after the model's knowledge cutoff — related
• All three LLM-generated feedback types are associated with faster time to solution than a compiler-errors-only baseline, with Single-Issue Feedback showing the largest reduction — related
• Student-voted Good feedback was associated with far fewer attempts and shorter solution times than Poor feedback, and thematic analysis identified outdated references and false positives as common failure modes — related
• Feedback type did not affect whether students solved assignments; solution rates were very similar across all conditions — related