Construction and Application of an AI-Native Vertical Intelligent Agent System for Teaching Based on the STS8200 Test Platform

Jingtian Guo; Qianmo Li; Guorui Lyu; Mengle Han; Shihan Zheng

doi:10.2991/978-94-6239-766-8_28

<Previous Article In Volume

Next Article In Volume>

Construction and Application of an AI-Native Vertical Intelligent Agent System for Teaching Based on the STS8200 Test Platform

Authors

Jingtian Guo¹^{, *}, Qianmo Li², Guorui Lyu³, Mengle Han⁴, Shihan Zheng¹

¹School of Integrated Circuits, North China University of Technology, Beijing, China

²Brunel London School, North China University of Technology, Beijing, China

³College of Science, North China University of Technology, Beijing, China

⁴School of Artificial Intelligence and Computer Science, North China University of Technology, Beijing, China

^*Corresponding author. Email: jingtiangrace@gmail.com

Corresponding Author

Jingtian Guo

Available Online 4 September 2026.

DOI: 10.2991/978-94-6239-766-8_28 How to use a DOI?
Keywords: Integrated Circuit Testing; STS8200; AI Agent; RAG Architecture; Educational Technology; Knowledge Graph
Abstract: Automatic Test Equipment (ATE) is a vital component of the semiconductor industrial chain. Its multidisciplinary attributes create substantial difficulties for novice learners in theoretical study, who also rely heavily on one-on-one guidance from teachers. To improve learning efficiency, this paper proposes an AI-native vertical intelligent agent system named ICAgent. This system innovatively adopts Large Language Models (LLMs) as the central orchestrator. It leverages a hybrid retrieval mechanism to enhance the accuracy of knowledge recall, and applies a single-model multi-role prompt engineering design to reduce deployment complexity. Experiments conducted on the STS8200 chip automatic test equipment show that the system achieves a core knowledge Q&A accuracy of 96.2% for ATE testing, an 87.5% accuracy rate for code error diagnosis, and a case retrieval response time of 2.8 seconds. Additionally, it supports 60 concurrent users with negligible queuing latency.
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 2026 6th International Conference on Education, Information Management and Service Science (EIMSS 2026)
Series: Atlantis Highlights in Computer Sciences
Publication Date: 4 September 2026
ISBN: 978-94-6239-766-8
ISSN: 2589-4900
DOI: 10.2991/978-94-6239-766-8_28 How to use a DOI?
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

ris enw bib

TY  - CONF
AU  - Jingtian Guo
AU  - Qianmo Li
AU  - Guorui Lyu
AU  - Mengle Han
AU  - Shihan Zheng
PY  - 2026
DA  - 2026/09/04
TI  - Construction and Application of an AI-Native Vertical Intelligent Agent System for Teaching Based on the STS8200 Test Platform
BT  - Proceedings of the 2026 6th International Conference on Education, Information Management and Service Science  (EIMSS 2026)
PB  - Atlantis Press
SP  - 270
EP  - 283
SN  - 2589-4900
UR  - https://doi.org/10.2991/978-94-6239-766-8_28
DO  - 10.2991/978-94-6239-766-8_28
ID  - Guo2026
ER  -

download .riscopy to clipboard