← शोध समाचार पर लौटें
Editorial cover for a randomized comparison of structured AI tutoring and active-learning physics classes
जर्नल पेपरPeer-reviewed study202520 जुल॰ 2026· 3 min

AI tutoring outperforms in-class active learning: an RCT introducing a novel research-based design in an authentic educational setting

Greg Kestin, Kelly Miller, Anna Klales, Timothy Milbourne, Gregorio Ponti

Scientific Reports

500-शब्द सार

Editorial cover for a randomized comparison of structured AI tutoring and active-learning physics classes

Kestin, Miller, Klales, Milbourne, and Ponti test whether a deliberately designed generative-AI tutor can match or exceed a strong classroom comparison rather than a passive lecture. Their open-access Scientific Reports article describes a randomized crossover experiment in a large introductory physics course at Harvard University. The central comparison is between an AI tutor built around established learning principles and an in-class active-learning lesson covering the same content.

The study involved 194 undergraduates and two consecutive lessons on surface tension and fluid flow. Students were divided into two groups. In the first week, one group completed an AI-supported lesson at home while the other attended the active-learning class; the conditions were reversed in the second week. Both groups completed a pre-test and post-test for each topic. The researchers also measured time on task and asked students about engagement, enjoyment, motivation, and growth mindset.

The tutor was not a generic chatbot. Physics instructors created question-specific prompts, structured the interaction to manage cognitive load, embedded content-rich explanations and videos, and required the model to scaffold the learner rather than simply provide answers. This design choice is crucial: the experiment evaluates a pedagogically engineered system operating inside a defined lesson, not unrestricted use of a general-purpose AI assistant.

Students in the AI-tutored condition achieved higher post-test scores. The median post-test score was 4.5 for the AI group and 3.5 for the in-class group, against a combined pre-test median of 2.75. The authors report that median learning gains were more than twice as large with the AI tutor and that the difference was statistically significant. Regression analyses controlling for prior physics knowledge, course performance, ChatGPT experience, topic, test version, and time on task produced a large estimated effect. The authors place the effect between 0.73 and 1.3 standard deviations after addressing a ceiling effect.

The AI condition was also faster for many learners. The classroom lesson provided about 60 minutes of learning time after tests, while the median AI-tutor time on task was 49 minutes; 70 percent of AI users spent less than 60 minutes. Students reported higher engagement in the AI condition and also rated enjoyment, motivation, and growth-mindset-related experience positively. The individualized pace and immediate feedback may help explain both the cognitive and affective results.

The findings need careful boundaries. This was a short intervention covering two physics topics at one selective university. The comparison was not a full course, and the post-tests measured immediate mastery rather than long-term retention, transfer, collaboration, or independent problem solving. The result may depend on GPT-4, expert-written prompts, high-quality instructional videos, a tightly structured framework, and content that fits stepwise tutoring. The authors explicitly caution that the tutor may not outperform classroom active learning for complex synthesis or higher-order critical thinking.

For AIEDHK, the paper offers a productive contrast to studies of unrestricted AI. The result does not show that any chatbot improves learning. It shows that pedagogical architecture can matter as much as model capability. Schools and universities considering AI tutors should document the tutor's instructional rules, compare it with a credible teaching practice, and measure retention and transfer after access is removed. A strong pilot would also examine who benefits, which learners disengage, how errors are handled, and how the tutor complements human discussion. The practical lesson is to evaluate a designed learning system—not merely access to a model.

संबंधित पेपर

Illustrative photograph of a teacher-education group discussing a short fictional tutoring exchange, with two alternative response cards on a seminar table.
टूल / डेटासेट2026
टूल / डेटासेट 249

Preprint: TutorCaseBench separates recognizing a strategy from responding to a learner

Yeon Su Park, Chanyoung Park, Tae Soo Kim, Seungju Kim, Hyunwoo Kim, Daho Jung, Jinsung Yoon, Juho Kim

arXiv preprint

A benchmark builds simulated tutoring cases from qualitative education studies. Models were more successful at choosing a proposed strategy than at generating a response adapted to the particular situation.

preprintAI tutor evaluationcase-based assessment
500-शब्द सार पढ़ें →
Illustrative photograph of campus support staff reviewing a classroom-equipment service ticket and a permissioned action flow on a workstation.
नीति / नैतिकता30 अक्टू॰ 2026
नीति / नैतिकता 250

Product news: OpenAI and ServiceNow connect workflow context with permissioned actions

OpenAI, ServiceNow

AI Product and Learning Report

An October 28 partnership update describes ServiceNow workflows in ChatGPT and planned Codex, security and voice capabilities. Universities can use the announcement to examine how an assistant moves from finding information to changing a record.

product newsChatGPTServiceNow
500-शब्द सार पढ़ें →
Two students and an instructor inspect polarizer components while comparing an annotated light-path diagram in an optics teaching laboratory.
जर्नल पेपर2025
जर्नल पेपर 172

AI feedback improved answers during an augmented-reality physics lab, while independent transfer was not assessed

Atakan Coban, David Dzsotjan, Stefan Küchemann, Jürgen Durst, Jochen Kuhn, Christoph Hoyer

EPJ Quantum Technology

A physics laboratory study compared feedback and no-feedback questions within an augmented-reality quantum-cryptography activity involving 21 student groups. GPT-4 feedback helped groups improve their immediate explanations, while gaze records suggested changes in attention to relevant representations and equipment. The measured outcome was answer improvement during supported discussion. A small voluntary sample, exploratory gaze analyses and no independent delayed test limit broader claims about learning and the value of the combined technology.

physics educationaugmented realityformative feedback
500-शब्द सार पढ़ें →