Leveraging “Khanmigo” Generative AI-Powered Tool for Personalized Tutoring to Learn Scientific Concepts
Bibliographic record
Abstract
This mixed-methods study investigated the effectiveness of Generative AI (GenAI) powered intelligent tutoring systems (ITS) in undergraduate physics education, specifically comparing learning outcomes between students using Khanmigo (Khan Academy's AI tutor) and Google search engine. The study involved 69 undergraduate students divided into two groups (Khanmigo and Google search engine), with a third Paper-only group emerging during the experiment. Participants completed pre and posttests using the Lunar Phases Concept Inventory (LPCI) and participated in structured interviews about their learning experiences. Quantitative analysis revealed significant learning gains across all conditions but found no statistically significant differences between groups in terms of learning outcomes. Qualitative findings indicated that students perceived Khanmigo positively, appreciated its step-by-step guidance, practice problems, and personalized interactions. However, students viewed it as a supplementary tool rather than a replacement for traditional instruction. The study's findings suggest that while GenAI-powered tutoring systems can effectively support learning, their immediate impact on learning outcomes may be comparable to traditional methods. However, the short duration of exposure to the AI tutor and the quality of the printed materials may have affected these results.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.007 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".