Skip to content
Review Open access

Multimodal Generative AI in Education: A Systematic Literature Review of Tasks, Modalities, and Methods

2026 · IEEE Access · Vol 14, pp. 161912-161923 · 0 citations · 45 references

TL;DR

This review maps where educational MLLM work is concentrated and identifies speech/audio-rich interaction and video-grounded classroom understanding as priority directions for future multimodal educational systems.

Abstract

Background: Multimodal Generative Artificial Intelligence (AI) is transforming educational technology by enabling systems to generate and interpret multiple forms of information, including text, images, diagrams, audio, and video, primarily through multimodal large language models (MLLMs). Prior reviews of AI in education have focused on text-based large language models or a single instructional domain, without quantifying how multimodal systems are distributed across educational tasks, modalities, and methods. Objective: This systematic literature review addresses that gap by examining current applications of multimodal generative AI in education through three questions: (1) What educational tasks are targeted, and how are they distributed? (2) Which modality configurations (text, image, speech/audio, video) are used, and which remain underexplored? (3) What methodological approaches are employed, and how are they distributed? Methods: Thirty-eight papers published between 2020 and January 19, 2026 were reviewed using a two-level coding strategy consisting of dominant categories and secondary tags across educational tasks, modality configurations, and methodological approaches. Results: The literature primarily focuses on learner-facing feedback, tutoring, and learning guidance (17 of 38 studies, 44.7%), followed by assessment, scoring, and evaluation (10 of 38, 26.3%) and learning-support utilities (8 of 38, 21.1%). Most systems employ vision-language (text and image) configurations (31 of 38, 81.6%), while video-inclusive (4 of 38, 10.5%) and speech/audio-dominant configurations (3 of 38, 7.9%) remain comparatively infrequent. Most studies report technical performance metrics rather than validated pedagogical outcomes. Conclusion: Current educational applications of multimodal generative AI concentrate on vision-language tutoring and evaluation, while video and speech/audio modalities and pedagogically validated evidence remain comparatively underexplored. This review maps where educational MLLM work is concentrated and identifies speech/audio-rich interaction and video-grounded classroom understanding as priority directions for future multimodal educational systems.

Read PDF

Similar papers

Open access 2026

AI-Customized Digital Picture Books to Enhance Vocabulary Learning in Early ELT Classrooms: A Quasi-Experimental Study

Artificial intelligence (AI) is increasingly shaping English language teaching by enabling personalized and multimodal instructional approaches. This study investigates the use of AI-customized digital picture books (DPBs) to enhance vocabulary learning in early primary classrooms. The novelty of this work lies in tran...

Unknown authors · 0 citations
Review Open access Nov 2026

The Use Of Artificial Intelligence (AI) As An Interactive Learning Tool For Students With Intellectual Disabilities In Special Education Schools

It is suggested that AI should complement, rather than replace, teachers' pedagogical judgment and individualized instruction in special education, and that classroom-based research is necessary to evaluate learning outcomes and long-term applicability.

Aceng Rosadi, M. Efendi, E. Ediyanto · 0 citations
Conference Open access Oct 2026

Beyond Audio: An Empirical Assessment of AI-Generated Podcasts and Videocasts in Business Education

Generative artificial intelligence (AI) is opening new possibilities for personalized, engaging instructional content in higher education. Extending our earlier work on AI-generated podcasts, this study examines the addition of AI-generated videocasts (video overviews) alongside podcasts in an undergraduate business an...

Gokhan Egilmez, K. Schneider · 0 citations
Review Open access Oct 2026

AI-Based Interactive Content Development through Activity-Based Training Design for Kindergarten Teachers: A Systematic Literature Review

Background: Artificial intelligence (AI) can expand teachers’ capacity to develop visual, multimodal, adaptive, and interactive learning content, but tool mastery alone does not ensure pedagogical competence. Recent reviews also indicate that teacher professional development (TPD) for AI remains less developed than res...

F. Arianto, B. Bachri, Nur Ainiyah et al. · 0 citations
Open access Oct 2026

AI and Immersive Technologies in Language Education

Artificial intelligence (AI) and immersive technologies are expanding opportunities for language learners to obtain feedback, revise writing, and rehearse communication. Their educational value depends on how these opportunities support learning and informed participation. Wu et al. (2025) locate recent technological d...

Wei-Lun Wong · 0 citations
#artificial intelligence Review Open access Oct 2026

Artificial Intelligence in Language Education: Pedagogical Applications, Representative Platforms, and Human Oversight

Artificial intelligence is reshaping language education through automated feedback, speech recognition, adaptive practice, dialogue systems, machine translation, learning analytics, and generative language models. This article critically reviews the principal pedagogical uses of these technologies and examines represen...

Sema Mehdi, Türkan İsmayıllı · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.