Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2604.12066 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908961550106624 |
|---|---|
| author | Walkington, Candace Beauchamp, Theodora Ikram, Fareya Gürbüz, Merve Koçyiğit Xia, Fangli Lee, Margan Lan, Andrew |
| author_facet | Walkington, Candace Beauchamp, Theodora Ikram, Fareya Gürbüz, Merve Koçyiğit Xia, Fangli Lee, Margan Lan, Andrew |
| contents | Large language models can increasingly adapt educational tasks to learners characteristics. In the present study, we examine a multi-agent teacher-in-the-loop system for personalizing middle school math problems. The teacher enters a base problem and desired topic, the LLM generates the problem, and then four AI agents evaluate the problem using criteria that each specializes in (mathematical accuracy, authenticity, readability, and realism). Eight middle school mathematics teachers created 212 problems in ASSISTments using the system and assigned these problems to their students. We find that both teachers and students wanted to modify the fine-grained personalized elements of the real-world context of the problems, signaling issues with authenticity and fit. Although the agents detected many issues with realism as the problems were being written, there were few realism issues noted by teachers and students in the final versions. Issues with readability and mathematical hallucinations were also somewhat rare. Implications for multi-agent systems for personalization that support teacher control are given. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_12066 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Mathematics Teachers Interactions with a Multi-Agent System for Personalized Problem Generation Walkington, Candace Beauchamp, Theodora Ikram, Fareya Gürbüz, Merve Koçyiğit Xia, Fangli Lee, Margan Lan, Andrew Artificial Intelligence Computers and Society Large language models can increasingly adapt educational tasks to learners characteristics. In the present study, we examine a multi-agent teacher-in-the-loop system for personalizing middle school math problems. The teacher enters a base problem and desired topic, the LLM generates the problem, and then four AI agents evaluate the problem using criteria that each specializes in (mathematical accuracy, authenticity, readability, and realism). Eight middle school mathematics teachers created 212 problems in ASSISTments using the system and assigned these problems to their students. We find that both teachers and students wanted to modify the fine-grained personalized elements of the real-world context of the problems, signaling issues with authenticity and fit. Although the agents detected many issues with realism as the problems were being written, there were few realism issues noted by teachers and students in the final versions. Issues with readability and mathematical hallucinations were also somewhat rare. Implications for multi-agent systems for personalization that support teacher control are given. |
| title | Mathematics Teachers Interactions with a Multi-Agent System for Personalized Problem Generation |
| topic | Artificial Intelligence Computers and Society |
| url | https://arxiv.org/abs/2604.12066 |