This paper focuses on the cutting-edge advancement of AI-empowered education, designing and implementing a personalized learning system empowered by knowledge graph and educational agent. For the Python course, semantic compression technology is used to distill student dialogues into cognitive labels in real time, building dynamic learning profiles and long-term companionship memory. Combined with intelligent agents and knowledge graph queries, heuristic tutoring is achieved, effectively suppressing AI hallucinations. The homework grading module features targeted traceability, automatically locating prerequisite knowledge nodes to form a closed loop of assessment and remediation. The system boasts both high-concurrency responsiveness and precise tutoring capabilities under low-computing-power conditions, significantly reducing teachers' workload and improving personalized learning outcomes.

Jiacheng Jin, Min Wang, Yuxuan Wang, Zitong Hui, Meng Li, Nian Liu. Design and Implementation of a Personalized Learning System Integrating Knowledge Graph and Lightweight Agent. The Frontiers of Society, Science and Technology (2026), Vol. 8, Issue 3: 32-38. https://doi.org/10.25236/FSST.2026.080305.

[1] Zhang Jiaqi. Research and Implementation of Course Question Answering System Combining Large Language Model and Knowledge Graph [D]. Huazhong University of Science and Technology, 2024. 

[2] AnMengliang. Design and Implementation of Intelligent Tutoring System Based on Knowledge Graph [D]. University of Chinese Academy of Sciences (Shenyang Institute of Computing Technology), 2021. 

[3] Wen Chao, Zhang Dandan, Zhang Jing, et al. Exploration of Personalized Learning Model Based on Artificial Intelligence Knowledge Graph Construction: Taking "Grassland Soil Biology" Undergraduate Course as an Example [J/OL]. Pratacultural Science, 1-11 [2026-06-04]. https://link-cnki-net-s.webvpn.bcu.edu.cn:8000/urlid/62.1069.S.20251107.1033.004.

[4] Zhang Xuefei, Zhang Liping, Yan Sheng, et al. Personalized Learning Recommendation Based on Synergy of Knowledge Graph and Large Language Model [J]. Journal of Computer Applications, 2025, 45 (3): 773-784.

[5] Tu Yixiao. Personalized Learning Recommendation Driven by Synergy of Knowledge Graph and Large Language Model: Framework Construction, Application Verification, and Future Trends [J]. Information & Computer, 2025, 37 (17): 27-29.

[6] Zhai Jie, Li Yanhao, Chen Lexuan, et al. Dynamic Recommendation of Personalized Practical Learning Materials Based on Lightweight Educational Large Model [J]. Computer Science, 2026, 53 (2): 48-56.

[7] Fang Haiguang, Deng Yang, Li Zeyu, et al. Exploration of New Personalized Learning Based on AI Agents from the Perspective of Human-Machine Collaboration [J]. Modern Educational Technology, 2026, 36 (2): 40-50.

[8] Zhang Wei, Gan Lu, Du Mengqi, et al. Precise Q&A System for Course Knowledge Integrating Knowledge Graph and Large Language Model [J]. Modern Information Technology, 2026, 10 (8): 113-117. 

[9] Cao Wei, Lu Shuping, Zhu Hongxu, et al. Research on the Development of Exclusive Agents Based on Personalized Teaching [J]. Vocational Technology, 2025, 24 (9): 37-43.

[10] Duan Dongsheng, Li Sihan. Design of Personalized Learning Evaluation System Combining AI-Driven Dynamic Graph and Agents [J]. Information System Engineering, 2025, (11): 157-160.

[11] The Central Committee of the Communist Party of China and the State Council. Outline of the Plan for Building a Leading Country in Education (2024–2035) [EB/OL]. (2025-01-19) [2025-04-28]. https://www.gov.cn/zhengce/202501/content_6999913.htm