Agentic education · Learning science

Actionable companion · Motivation & engagement

Learning with agency: Avatars in the educational metaverse

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): Age / stage not established. Verify the participant population and task before transferring the findings.

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

Abstract Avatars in the educational metaverse are revolutionizing the learning process by providing interactive and effective learning experiences. These avatars enable students to engage in realistic scenarios, work in groups, and develop essential skills using adaptive and intelligent technologies. The purpose of this review is to evaluate the contribution of avatars to education. It investigated the use of avatars to enhance learning by offering individualized experiences and supporting collaborative group activities in virtual environments. It also analyzed the recent progress in artificial intelligence, especially natural language processing and generative models, which have significantly improved avatar capabilities. In addition, it reviewed their use in customized learning, contextual teaching, and virtual simulations to improve student participation and achievement. This study also highlighted issues impacting its implementation, including data security, ethical concerns, and limited infrastructure. The paper ends with implications and recommendations for future research in this field. Keywords: Avatars, Metaverse, Artificial intelligence, Virtual environments, Data security

What kind of evidence is this?

Supporting AI learning science · Evidence synthesis

Stage: Age / stage not established. 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.

Limitations and uncertainty · source passage

Several areas exist where AI-based educational avatars have not been fully explored, offering promising avenues for future research. One critical area is the integration of digital twins and real-world data into educational applications. Although avatars can process data from these sources, there is a need to investigate how such data can be meaningfully utilized to enhance learning experiences. For instance, real-time data from the Internet of Things devices or simulations can be leveraged to create adaptive, context-aware learning environments that respond dynamically to student needs. This could involve exploring how avatars can act as intermediaries between students and complex datasets, simplifying information and guiding learners through real-world problem-solving scenarios.

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.

  • Measure engagement separately from achievement. Check whether novelty-driven participation persists and whether it translates to independent performance.

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. Treat the paper as background evidence until its population is verified in the full text. Do not assign an age-specific intervention or extend adult results to children. 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. Extract the participant ages or education stage, recruitment, task and comparator before selecting a local pilot. If these cannot be established, retain the paper for design discussion rather than age-band efficacy claims. 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

Md Zabirul Islam; Ge Wang. Avatars in the educational metaverse. Visual Computing for Industry, Biomedicine, and Art (2025-06-10). https://doi.org/10.1186/s42492-025-00196-9

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.