Agentic education · Learning science

Actionable companion · Learning design & outcomes

Learning with agency: Effects of exergames on student physical education learning in the context of the artificial intelligence era: a meta-analysis

AI-assisted editorial implementation guide, separate from the original research. Proposed actions are not claims or recommendations attributed to the source authors. No independent peer review of this guide is asserted.

Read original paperSearch paper agentCC BY 4.0

Evidence and context

Title and abstract screening; stage labels describe reported settings, not verified numerical ages. Design labels require full-text appraisal. Reported stage(s): Early childhood · preschool. Verify the participant population and task before transferring the findings.

Original authors’ abstract, reproduced under the linked source license:

Whether the application of exergames in physical education (PE) courses can significantly improve student performance in PE learning is still controversial. This review explores the promoting effect of exergames on student PE learning and the conditions in which the effect of exergames can be maximized. Based on the PICOS method, two researchers independently searched the ProQuest database, EBSCO database, Web of Science (WoS) database, PubMed database, Chinese National Knowledge Infrastructure (CNKI) database, Wanfang database, and VIP database, evaluated the literature quality using the Cochrane system evaluation manual, and performed a meta-analysis of the included literature. A total of 16 randomized controlled trials involving 2962 subjects were included in this study. The meta-analysis showed that exergames effectively improved student performance in PE learning (SMD = 0.45, 95% CI: 0.27–0.63, P < 0.00001). Subgroup analysis indicated that better results could be achieved when exergames were introduced in small kindergarten classes and continued for 1–2 months.

What kind of evidence is this?

Supporting AI learning science · Evidence synthesis

Stage: Early childhood · preschool. Screening labels describe reported context and study-design language. They are not a risk-of-bias rating or proof of effectiveness for an age band.

Study methods · source passage

The databases include Chinese National Knowledge Infrastructure (CNKI), Wanfang, VIP, Web of Science (WoS), ProQuest, PubMed, and EBSCO, and the search period was set from January 2001 to November 2023. To ensure the comprehensiveness of the literature search, the subject terms of the Chinese search were set as "games", containing "sports", "effect or performance or application or practice or impact", etc. The search for foreign articles was mainly conducted with subject headings 1 (game or gamification or game-based or gamifying or gamified or exergame or exergaming or AVG), subject headings 2 ("physical education" or PE), and subject headings 3 (performance or outcome or achievement or effect or score or experiment). The search also covered relevant reviews and references of included studies to minimize the number of missed articles. The languages of all included literature were Chinese and English. To ensure the high quality and scientific validity of the included studies, the included Chinese literature was obtained from core journals and CSSCI journals, and the English literature was sourced from SCI and SSCI journals.

Design the system before the pilot

Use this study to inform a learning mechanism or implementation question. It is not direct evidence that autonomous agents improve learning. Keep the proposed agent behavior separate from what the source actually tested.

  • Specify a measurable learning objective, a comparator and a task without tool assistance before adopting a system.

A 90-day district pilot

  1. Days 1–15 · Appraise. Have the curriculum lead and a teacher read the methods and limitations. Record the study design, sample, comparator, outcomes and evidence gaps. Define a local question that the study can help inform.
  2. Days 16–30 · Design. Use a brief adult-mediated story, turn-taking or language activity. An educator controls every interaction; the agent never becomes an unsupervised companion. Preserve hands-on play and human conversation. Name an accountable owner and set the baseline, success threshold and budget before implementation.
  3. Days 31–60 · Test. Start with a small voluntary cohort, preserve an accessible non-AI route and require teacher review. Use synthetic or de-identified examples; approve data handling and tool terms through district processes.
  4. Days 61–90 · Decide. Measure independent naming, explanation or turn-taking in a human-led activity after the tool is removed. Record frustration, overstimulation and the amount of adult help. Compare with baseline, document uncertainty and stop or revise if learning worsens, access is unequal or critical errors persist.

The board decision brief

Report the learning problem, evidence quality, participating population, total cost including review time, measured benefit, errors, access differences and remaining uncertainties. Make a dated recommendation to stop, revise or expand. A positive perception survey alone does not establish learning improvement.

Attribution and reuse

Mengnan Zhao; Xurui Lu; Qi Zhang; Rutong Zhao; Bohang Wu; Sheng Huang; Sunnan Li. Effects of exergames on student physical education learning in the context of the artificial intelligence era: a meta-analysis. Scientific Reports (2024-03-26). https://doi.org/10.1038/s41598-024-57357-8

Companion prepared 2026-10-30. Original authorship and DOI are preserved. The abstract is an attributed source extract; the implementation plan is new AI-assisted editorial material, offered under the same CC BY 4.0 license. This guide has not undergone independent peer review.