Skip to content
#generative ai Open access

TEAM (Teacher Empowered Assessment Movement): A Teacher-Led Ecosystem Framework of Generative AI Agents for Adaptive Learning — An English-language technical report of Research Project No. 2025-1-09

Sep 2026 · Zenodo (CERN European Organization for Nuclear Research) · 4 citations

Abstract

This is an English-language technical report of a study reported in full, in Korean, as Research Project No. 2025-1-09 under Korea's Educational Development Special Zone — Digital Education Innovation Project. It introduces no data, analysis, or claim absent from the Korean report. The study compared the centralized platform (CP) model, as instantiated in Korea's AI Digital Textbook programme, with a decentralized ecosystem (DE) model in which teachers design, build and operate their own generative AI agents. Work ran from June to November 2025 in four stages: theoretical grounding; a survey and focus group study of teacher perception and requirements; a teacher-led agent development programme; and the formulation of a CP–DE hybrid framework. Twenty-four teachers completed the first survey; 22 had used the AI Digital Textbook. They rated the difficulty of getting teacher feedback reflected in the platform as its most serious limitation (79.2%), while recognising access (45.8%) and curricular consistency (41.7%) as genuine strengths. Perceived necessity of a teacher-led alternative was M = 4.71 and intention to participate M = 4.67. Topic modelling of focus group transcripts (K = 5) returned topics dominated by the limits of centralized AI and by teachers' identification with a maker rather than user role. A 30-session capacity-building track was developed and run, and participating teachers designed and deployed working agents in their own classrooms. The study establishes what teachers report needing and demonstrates that teachers without programming backgrounds can build usable agents. It does not measure whether teacher-built agents improve assessment quality or learning outcomes, and it contains no operational record of how often teachers revised or rejected agent output. Funded by the Educational Development Special Zone — Digital Education Innovation Project, Ministry of Education and Daegu Metropolitan Office of Education, and the AI–Digital Convergence Education Innovation Platform, Kyungpook National University. Project No. 2025-1-09.

View source

Similar papers

#artificial intelligence Conference Open access Apr 2020

ECCOLA - a Method for Implementing Ethically Aligned AI Systems

The method, ECCOLA, is presented, which aims at making the high-level AI ethics principles more practical, making it possible for developers to more easily implement them in practice.

Ville Vakkuri, Kai-Kristian Kemell, P. Abrahamsson · 64 citations · ⚡6
#computer vision Review Apr 2024

AI-powered Code Review with LLMs: Early Results

The goal is to not only refine the accuracy of the LLM-based tool but also to underscore its potential in streamlining the software development lifecycle through proactive code improvement and education.

Z. Rasheed, Malik Abdul Sami, Muhammad Waseem et al. · 62 citations · ⚡3
#computer vision Open access Mar 2024

LLM-based agents for automating the enhancement of user story quality: An early report

The use of large language models to automatically improve the user story quality in Austrian Post Group IT agile teams is explored, with a reference model for an Autonomous LLM-based Agent System developed and implemented at the company.

Zheying Zhang, M. Rayhan, Tomas Herda et al. · 48 citations · ⚡4
#computer vision Review Mar 2024

System for systematic literature review using multiple AI agents: Concept and an empirical evaluation

This paper introduces a novel multi-AI-agent system designed to fully automate SLRs, and demonstrates how it substantially reduces the time and effort traditionally required for SLRs while maintaining comprehensiveness and precision.

Abdul Malik Sami, Z. Rasheed, Kai-Kristian Kemell et al. · 44 citations · ⚡2
#computer vision Feb 2024

Can Large Language Models Serve as Data Analysts? A Multi-Agent Assisted Approach for Qualitative Data Analysis

The proposed LLM-based multi-agent system automates qualitative data analysis process, creating opportunities for researchers and practitioners, and future improvements focus on enhancing multilingual performance and integrating continuous expert feedback.

Z. Rasheed, Muhammad Waseem, Aakash Ahmad et al. · 41 citations

Related blog posts

GPT-Lab Sep 17, 2026

Beyond Prompt Engineering: The Role of Tacit Knowledge in Software Engineering

AI is making software generation faster, but speed does not remove the need for expertise. As more work is delegated to AI, tacit knowledge may become one of the most important human advantages in software engineering. The post Beyond Prompt Engineering: The Role of Tacit Knowledge in Software Engineering appeared first on GPT-Lab.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.