Intelligent Teaching Design Assistant for Primary Mathematics: A Large Language Model-Driven Framework with Retrieval-Augmented Generation and Problem-Chain Pedagogy
Saved in:
| Title: | Intelligent Teaching Design Assistant for Primary Mathematics: A Large Language Model-Driven Framework with Retrieval-Augmented Generation and Problem-Chain Pedagogy |
|---|---|
| Language: | English |
| Authors: | Danna Tang (ORCID |
| Source: | International Electronic Journal of Mathematics Education. 2026 21(1). |
| Availability: | International Electronic Journal of Mathematics Education. Suite 124, Challenge House 616 Mitcham Road, CR0 3AA, Croydon, London, UK. Tel: +44-208-936-7681; e-mail: iejme@iejme.com; Web site: https://www.iejme.com |
| Peer Reviewed: | Y |
| Page Count: | 12 |
| Publication Date: | 2026 |
| Document Type: | Journal Articles Reports - Research |
| Education Level: | Elementary Education |
| Descriptors: | Elementary School Mathematics, Mathematics Education, Intelligent Tutoring Systems, Elementary School Teachers, Mathematics Teachers, Artificial Intelligence, Technology Uses in Education, Program Effectiveness, Usability, Value Judgment |
| ISSN: | 1306-3030 |
| Abstract: | Primary mathematics education faces systemic challenges in translating curriculum reforms into classroom practice, exacerbated by teachers' cognitive overload and limited support for pedagogical innovation. This study develops an Intelligent Teaching Design Assistant grounded in socio-constructivist and cognitive load theories to address these challenges. Thirty-four primary mathematics teachers participated in a quasi-experimental study. The Intelligent Teaching Design Assistant integrates Large Language Models with multi-dimensional knowledge bases (curriculum standards, teaching strategies, student profiles) and a multi-agent architecture (process planner, student simulator). The Intelligent Teaching Design Assistant significantly outperformed generic Large Language Models, improving overall lesson plan quality. This work pioneers a replicable pathway for AI to empower teacher agency and advance 21st-century educational transformation. |
| Abstractor: | As Provided |
| Entry Date: | 2026 |
| Accession Number: | EJ1505528 |
| Database: | ERIC |
| Abstract: | Primary mathematics education faces systemic challenges in translating curriculum reforms into classroom practice, exacerbated by teachers' cognitive overload and limited support for pedagogical innovation. This study develops an Intelligent Teaching Design Assistant grounded in socio-constructivist and cognitive load theories to address these challenges. Thirty-four primary mathematics teachers participated in a quasi-experimental study. The Intelligent Teaching Design Assistant integrates Large Language Models with multi-dimensional knowledge bases (curriculum standards, teaching strategies, student profiles) and a multi-agent architecture (process planner, student simulator). The Intelligent Teaching Design Assistant significantly outperformed generic Large Language Models, improving overall lesson plan quality. This work pioneers a replicable pathway for AI to empower teacher agency and advance 21st-century educational transformation. |
|---|---|
| ISSN: | 1306-3030 |
