# Multi-Agent Collaborative Framework For Math Problem Generation

arXiv: https://arxiv.org/abs/2511.03958 · HTML: https://mlsanity.com/paper/2511.03958/

## Key facts

- Cited by 5 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 16 of its 22 references that are in the map.
- First posted on arXiv 6 Nov 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, 16 of 16)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (2024)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society](https://mlsanity.com/paper/2303.17760/) (2023)
- [Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate](https://mlsanity.com/paper/2305.19118/) (2023)
- [Benchmarking Cognitive Biases in Large Language Models as Evaluators](https://mlsanity.com/paper/2309.17012/) (2023)
- [AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks](https://mlsanity.com/paper/2403.04783/) (2024)
- [The Oscars of AI Theater: A Survey on Role-Playing with Language Models](https://mlsanity.com/paper/2407.11484/) (2024)
- [Automated Educational Question Generation at Different Bloom's Skill Levels using Large Language Models: Strategies and Evaluation](https://mlsanity.com/paper/2408.04394/) (2024)
- [Math Word Problem Generation with Mathematical Consistency and Problem Context Constraints](https://mlsanity.com/paper/2109.04546/) (2021)
- [QGEval: Benchmarking Multi-dimensional Evaluation for Question Generation](https://mlsanity.com/paper/2406.05707/) (2024)
- [DHP Benchmark: Are LLMs Good NLG Evaluators?](https://mlsanity.com/paper/2408.13704/) (2024)
- [A Novel Approach to Scalable and Automatic Topic-Controlled Question Generation in Education](https://mlsanity.com/paper/2501.05220/) (2025)

## Built on by (most cited first, 5 of 5)

- [Enhancing Diversity of LLM-Generated Educational Tasks](https://mlsanity.com/paper/2512.23601/) (2025)
- [Latent-DARM: Bridging Discrete Diffusion And Autoregressive Models For Reasoning](https://mlsanity.com/paper/2603.09184/) (2026)
- [A self-evolving multi-role collaborative framework with fine-grained difficulty guidance for innovative mathematical problem generation](https://mlsanity.com/paper/2601.11792/) (2026)
- [A Multi-Agent Approach to Validate and Refine LLM-Generated Personalized Math Problems](https://mlsanity.com/paper/2604.05160/) (2026)
- [Lect=uraAgents: A Multi-Agent Framework for Adaptive Personalized AI-Assisted Learning and Embodied Teaching](https://mlsanity.com/paper/2606.16428/) (2026)

## Abstract (arXiv)

Automatic question generation (AQG) for mathematics education remains an elusive goal for Intelligent Tutoring Systems and educators. While pre-trained transformer-based language models have significantly advanced natural language generation, they often struggle to precisely control problem complexity and cognitive demands. In this paper, we introduce a collaborative multi-agent framework as a novel method of incorporating inference-time computation into AQG. This approach leverages multiple agents that iteratively refine generated question-answer pairs to better balance complexity and cognitive demand. We evaluate the generated questions on five meta-evaluation criteria: relevance, importance, clarity, difficulty matching, answerability, to assess the system's ability to control the required complexity and quality of the questions. Preliminary evaluations show that this collaborative multi-agent framework elevates the quality of generated educational content by fostering a more nuanced balance between cognitive challenge and clarity. These promising outcomes suggest that integrating collaborative multi-agent workflows can yield more controlled, pedagogically valuable content that can help advance automated educational content generation and adaptive learning environments.