LLM Agent Collaboration for Educational Strategy Design
International Conference on Computers in Education · 01.12.2025
DOI: 10.58459/icce.2025.6099 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Conference on Computers in Education, online erschienen am 01.12.2025. Verfasst von Bjanka VRLJIĆ und 2 weiteren Autor:innen.
Abstract (Originalsprache)
Large language models (LLMs) can be organized into multi-agent systems (MAS) that simulate expert panels, but coordination remains a challenge. In education, effective support often requires integrating insights from data analytics, curriculum design, and pedagogy. We present a moderated, embedding-driven MAS framework for educational decision-making. Role-specialized LLM agents generate structured recommendations, which are embedded into a shared semantic space. A central moderator measures alignment and agreement, computes a consensus embedding, and translates it back into natural language. This consensus is returned to the agents in subsequent rounds, guiding convergence while preserving distinct perspectives. A simulated case study illustrates the process in the context of secondary education. The results highlight the potential of embedding-based moderation to produce coherent, interpretable recommendations.
Zitieren
APA
VRLJIĆ, B., BOTIČKI, I., & POJE, K. (2025). LLM Agent Collaboration for Educational Strategy Design. International Conference on Computers in Education. https://doi.org/10.58459/icce.2025.6099
Vancouver
VRLJIĆ B, BOTIČKI I, POJE K. LLM Agent Collaboration for Educational Strategy Design. International Conference on Computers in Education. 2025. doi:10.58459/icce.2025.6099
BibTeX
@article{VRLJI2025,
author = {VRLJIĆ, Bjanka and BOTIČKI, Ivica and POJE, Kristijan},
title = {LLM Agent Collaboration for Educational Strategy Design},
journal = {International Conference on Computers in Education},
year = {2025},
doi = {10.58459/icce.2025.6099}
}
EUVIMED