Proceedings of the International Conference on Cross- Disciplinary Academic Research 2025 - Track 1 Advances in Computing, Electronics, Engineering, and Mathematics (ICAR-T1 2025)

<Previous Article In Volume
Next Article In Volume>

C.A.T.E.: A Multimodal AI Agent for Context-Aware and Bilingual Learning in Technical Education

Authors
Siti Robaya Jantan1, *, Ummi Haani Shahrul1, Roslinda Murad1
1Universiti Poly-Tech Malaysia, Jalan 6/91, Taman Shamelin Perkasa, 56100, Kuala Lumpur, Malaysia
*Corresponding author. Email: robaya@uptm.edu.my
Corresponding Author
Siti Robaya Jantan
Available Online 28 April 2026.
DOI
10.2991/978-94-6239-636-4_6How to use a DOI?
Keywords
AI Agents; Context-Aware Systems; GraphQL Integration; Large Language Models; Multimodal Learning; Technical Education
Abstract

The new large language models (LLMs), it is impressive in their generality, remain inadequate in terms of context-awareness, tool integration, and real-time flexibility that technical education requires. We offer a solution to this problem by introducing C.A.T.E. (Compiler Assistant for Technical Enhancement), a domain-specific, multimodal AI agent. Operating with an agile methodology and powered by LangGraph orchestration on GraphQL, C.A.T.E. incorporates third-party applications such as YouTube, Wikipedia, Google Books, and Wolfram Alpha. The system was tested by more than 30 participants from UPTM and UMT, with results indicating 92% satisfaction rate and receiving commendation for relevance, clarity, and technical accuracy. C.A.T.E. was able to consistently beat mainstream LLMs in controlled comparisons by providing task-specific, localized, and pedagogically practical assistance. This study demonstrates how LLM-based agent-powered tools, such as C.A.T.E., can transform the world of education through easily accessible, trustworthy, and highly contextual AI-based learning assistance.

Copyright
© 2026 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

<Previous Article In Volume
Next Article In Volume>
Volume Title
Proceedings of the International Conference on Cross- Disciplinary Academic Research 2025 - Track 1 Advances in Computing, Electronics, Engineering, and Mathematics (ICAR-T1 2025)
Series
Advances in Engineering Research
Publication Date
28 April 2026
ISBN
978-94-6239-636-4
ISSN
2352-5401
DOI
10.2991/978-94-6239-636-4_6How to use a DOI?
Copyright
© 2026 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Cite this article

risenwbib
TY  - CONF
AU  - Siti Robaya Jantan
AU  - Ummi Haani Shahrul
AU  - Roslinda Murad
PY  - 2026
DA  - 2026/04/28
TI  - C.A.T.E.: A Multimodal AI Agent for Context-Aware and Bilingual Learning in Technical Education
BT  - Proceedings of the International Conference on Cross- Disciplinary Academic Research 2025 - Track 1 Advances in Computing, Electronics, Engineering, and Mathematics (ICAR-T1 2025)
PB  - Atlantis Press
SP  - 57
EP  - 70
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6239-636-4_6
DO  - 10.2991/978-94-6239-636-4_6
ID  - Jantan2026
ER  -