An Optimization Path for "Supervisor-Counselor" Collaborative Education in Universities Empowered by Large Language Models
DOI:
https://doi.org/10.54097/m1pg6g15Keywords:
Large language models, supervisor-counselor collaboration, precision education, human-machine symbiosis, positive-sum gameAbstract
The deep integration of large language model (LLM) technology offers a transformative opportunity to break the long-standing zero-sum game dilemma in graduate "supervisor-counselor" collaborative education. This paper proposes a value orientation grounded in the concepts of "precision, synergy, integration, and symbiosis," and guided by the practical principles of "technological support, multi-stakeholder cooperation, resource sharing, and dynamic adjustment," to construct an optimized path system for university "supervisor-counselor" collaborative education in the context of LLMs. On this basis, it proposes reshaping a positive-sum game pattern featuring the deep integration of "academic and ideological-political education" under a fourfold guarantee of institution, platform, capability, and culture, thus providing an operable practical scheme for enhancing the management and service capacity of graduate education.
Downloads
References
[1] Zhang, J., & Zhang, Q. J. (2021). Collaborative education of graduate supervisors and counselors—Value implications, realistic dilemmas, and path selection. Journal of Graduate Education, (1), 22–28.
[2] Chen, L., Wang, J. C., & Guo, Q. H. (2025). Research on the path to strengthen "supervisor-counselor" collaborative education for graduate students in the new era. Journal of University of Science and Technology Beijing (Social Sciences Edition), 41(2), 43–49.
[3] Kang, X. X. (2022). The dilemma and breakthrough in constructing a collaborative education mechanism between graduate supervisors and counselors. Academic Degrees and Graduate Education, (5), 62–68.
[4] Guo, J. X., Fu, X., Wu, Z. A., et al. (2024). Innovative research on the heart-to-heart talk work of university counselors and top-notch students in the context of artificial intelligence. Journal of Ningxia Normal University, 45(11), 12–17.
[5] Parker, L., Carter, C., Karakas, A., et al. (2024). Graduate instructors navigating the AI frontier: The role of ChatGPT in higher education. Computers and Education Open, 6, 100166. https://doi.org/10.1016/j.caeo.2024.100166
[6] Chrysafiadi, K., & Virvou, M. (2013). Student modeling approaches: A literature review for the last decade. Expert Systems with Applications, 40(11), 4715–4729. https://doi.org/10.1016/j.eswa.2013.01.028
[7] Belle, L., & Yingling, B. (2023). A preliminary study on graduate student instructors' exploration, perception, and use of ChatGPT. International Journal of Computer-Assisted Language Learning and Teaching, 13(1), 1–23. https://doi.org/10.4018/IJCALLT.318346
[8] Shi, W. H. (2021). The internal logic and practical path of collaborative education between graduate supervisors and counselors. Studies in Ideological Education, (3), 130–134.
[9] Haken, H. (1989). Advanced synergetics (Z. A. Guo, Trans.). Science Press, pp. 23–45.
[10] Ren, M. (2021). A game analysis of collaborative education between supervisors and counselors in graduate education. Academic Degrees and Graduate Education, (8), 61–66.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Academic Journal of Applied Sciences
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
