# A LLM-Driven Multi-Agent Systems for Professional Development of Mathematics Teachers

arXiv: https://arxiv.org/abs/2507.05292 · HTML: https://mlsanity.com/paper/2507.05292/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Educational agents and math problem solving, one of 16 directions in LLM agents and tool use.
- Builds on 5 of its 16 references that are in the map.
- First posted on arXiv 5 Jul 2025.

## Placed in

- LLM agents and tool use / [Educational agents and math problem solving](https://mlsanity.com/agents/educational-agents-and-math-problem-solving/)

## Builds on (most cited first, 5 of 5)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [A Survey on In-context Learning](https://mlsanity.com/paper/2301.00234/) (2022)
- [A LLM-Powered Automatic Grading Framework with Human-Level Guidelines Optimization](https://mlsanity.com/paper/2410.02165/) (2024)
- [Knowledge Tagging System on Math Questions via LLMs with Flexible Demonstration Retriever](https://mlsanity.com/paper/2406.13885/) (2024)

## Built on by (most cited first, 1 of 1)

- [A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence](https://mlsanity.com/paper/2507.21046/) (2025)

## Abstract (arXiv)

Professional development (PD) serves as the cornerstone for teacher tutors to grasp content knowledge. However, providing equitable and timely PD opportunities for teachers poses significant challenges. To address this issue, we introduce I-VIP (Intelligent Virtual Interactive Program), an intelligent tutoring platform for teacher professional development, driven by large language models (LLMs) and supported by multi-agent frameworks. This platform offers a user-friendly conversational interface and allows users to employ a variety of interactive tools to facilitate question answering, knowledge comprehension, and reflective summarization while engaging in dialogue. To underpin the functionality of this platform, including knowledge expectation analysis, response scoring and classification, and feedback generation, the multi-agent frameworks are leveraged to enhance the accuracy of judgments and mitigate the issue of missing key points.