· Ph.D. · Senior Member, IEEE
This paper investigates ongoing trends in AI-based authoring tools within the context of large language models and examines how these tools support higher education through personalization of learning choices, habits, and emotional needs. It scrutinizes the design factors for effective AI-supported learning and authoring systems and proposes characteristics for next-generation tools that align with learner attitude and aptitude. The analysis considers cognitive diversity among engineering students and discusses future human-in-the-loop approaches to ensure rigor, reduce bias, and preserve human creativity.
The academic sphere has experienced flourishing growth in artificial intelligence and related verticals. This expansion has accelerated the development of sophisticated applications designed to foster prompts and follow-ups essential for day-to-day academic targets, including content creation endeavors, generating diversified simulation scenarios, examples, and quizzes, and shaping destination knowledge for students. The impact of such AI-driven authoring tools has become significant in engineering education, where practical behavioral and cognitive attributes of learners play crucial roles. Specifically, the support to tune to the impetus and diversified mental wisdom of learners raises the question of how far AI-based authoring tools can enrich the cognitive uplift of the learners. The objective of engineering education is not only the completion of the curriculum. It is also to generate more curious minds within engineering pedagogy. This article investigates both sides of AI improvisations in content creation and authoring for conventional teaching purposes and outlines the organization of the remaining sections.
By definition, e-learning authoring tools are software applications used to create digital training content such as courses, quizzes, simulations for demonstrations, and support for subsequent valuation of learners. Authoring tools foster instructional designers and educators in building interactive, enriched multimedia learning experiences, often without complex coding. Content can be delivered through an LMS or shared directly with learners. Core AI features include author assistance, dynamic content creation, content document rendering, and analytics and insights. Enabling technologies include natural language processing, machine learning, content curation, image and voice recognition, procedural content generation, and document layout analysis.
Cognition is the rudimentary ability through which humans understand, process, and apply information. Cognitive ability and traits of learners strongly influence the design of pedagogy and content generation. Higher order cognitive abilities such as creativity and critical thinking have a dominating impact within AI-based authoring. Personal characteristics and spontaneous states, including demographic variables, self-efficacy, learning habits, and emotional needs, as well as growth experiences across educational exposure and social-environmental interactions, shape psychological and intellectual development. Precise AI-based authoring applications should comprehend these attributes and emphasize personalized and accessible learning curves.
Figure 1. Futuristic version of a cognitive and personalized AI-based authoring tool.
Insert figure if available.
Authenticity and quality assurance remain concerns for academic reliability. Human-in-the-loop processes and fact-checking are necessary to maintain precision and relevance, particularly in engineering content. Reinforcement learning from human feedback can align outcomes with human goals. Bias in training data can be reflected and amplified by AI systems, which demands continuous auditing and mitigation. Excessive dependence on automation can undermine human creativity. Human-AI co-creativity suggests that future authoring tools should balance automation with human judgment and enable diverse simulation and game-based approaches where appropriate. The aim is to map personalized cognitive abilities of learners rather than rely on a single prompt.
This article summarizes artifacts of AI-based authoring tools, the relevance of learner cognitive features, and the scope for future integrations toward more realistic, cognitively aligned authoring systems. The comparative analysis of existing tools highlights opportunities and constraints. The future of AI-driven authoring appears promising if personalized cognitive abilities are mapped well and if human oversight preserves academic rigor, ethical alignment, and creativity.
1 Correspondence concerning this article should be addressed to Dr. Soumya Banerjee. For academic inquiries, please connect via
LinkedIn.
References formatted in APA 7 style where possible.
Baker, D. P., et al. (2015). The cognitive impact of the education revolution: A possible cause of the Flynn Effect on population IQ. Intelligence, 49, 144–158. https://doi.org/10.1016/j.intell.2015.01.003
Gunasekara, S., & Saarela, M. (2025). Explainable AI in education: Techniques and qualitative assessment. Applied Sciences.
Ahmed, A. A. A., & Ganapathy, A. (2021). Creation of automated content with embedded artificial intelligence: A study on learning management system for educational entrepreneurship. Academy of Entrepreneurship Journal, 27(3), 1–10.
Ayan Banerjee, S., Lladós, J., & Pal, U. (2024). Semidocseg: Harnessing semi-supervised learning for document layout analysis. International Journal on Document Analysis and Recognition.
Liang, H., Yang, L., Cheng, H., Tu, W., & Xu, M. (2017). Human-in-the-loop reinforcement learning. In 2017 Chinese Automation Congress (CAC) (pp. 4511–4518). https://doi.org/10.1109/CAC.2017.8243575
Lambert, N., Castricato, L., von Werra, L., & Havrilla, A. (2022). Illustrating reinforcement learning from human feedback (RLHF). Hugging Face Blog.
Altmann, P. R., et al. (2025). Discriminative reward co-training. Neural Computing and Applications.
Nyembo Mpampi, A. (2025). Bias in content-generating AI algorithms: Technical analysis, detection, and mitigation with Python. International Journal of Mathematics and Computer Research, 13(4), 5087–5095.
Hanna, M. G., et al. (2025). Ethical and bias considerations in artificial intelligence and machine learning. Modern Pathology, 38(3).
Haase, J., & Pokutta, S. (2024). Human-AI co-creativity: Exploring synergies across levels of creative collaboration. arXiv preprint.
Cristea, A. (2007). Authoring of adaptive educational hypermedia. In Seventh IEEE International Conference on Advanced Learning Technologies (ICALT) (pp. 943–944).
Sharp, D., et al. (1979). Education and cognitive development: The evidence from experimental research. Monographs of the Society for Research in Child Development, 44(1–2), 1–112. https://doi.org/10.2307/3181586
Brandt, N. D., Lechner, C. M., Tetzner, J., & Rammstedt, B. (2020). Personality, cognitive ability, and academic performance: Differential associations across school subjects and tracks. Journal of Personality, 88(2), 249–265. https://doi.org/10.1111/jopy.12482
Li, Z., & Qiu, Z. (2018). How does family background affect children’s educational achievement? Evidence from contemporary China. Journal of Chinese Sociology, 5(1), 1–21. https://doi.org/10.1186/s40711-018-0083-8
Iqbal, J., Asghar, M. Z., Ashraf, M. A., & Yi, X. (2022). The impacts of emotional intelligence on students’ study habits in blended learning environments. Behavioral Sciences, 12(1), 14.
Jansen, K., & Kiefer, S. M. (2020). Understanding brain development: Investing in young adolescents’ cognitive and social-emotional development. Middle School Journal, 51(4), 18–25. https://doi.org/10.1080/00940771.2020.1787749
Sharma, S., & Gupta, B. (2023). Technostress, cognitive appraisal, and coping strategies in higher education. Information Technology & People, 36(2), 626–660. https://doi.org/10.1108/itp-06-2021-0505
Niu, T., Liu, T., Luo, Y. T., Pang, P. C., Huang, S., & Xiang, A. (2025). Decoding student cognitive abilities: A comparative study of explainable AI algorithms in educational data mining. Scientific Reports, 15(1), 26862.
Maleki, M. F., & Zhao, R. (2024). Procedural content generation in games: A survey with insights on emerging LLM integration. In Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, 20(1).
Ahmadian, A., Cremer, C., Gallé, M., Fadaee, M., Kreutzer, J., Pietquin, O., Üstun, A., & Hooker, S. (2024). Back to basics: Revisiting reinforce style optimization for learning from human feedback in LLMs. arXiv preprint.