Multi-Agent Collaborative Framework For Math Problem Generation

• URL: http://arxiv.org/abs/2511.03958v1
• Date: Thu, 06 Nov 2025 01:24:07 GMT
• Title: Multi-Agent Collaborative Framework For Math Problem Generation
• Authors: Kia Karbasi, Kevin Hong, Mohammad Amin Samadi, Gregory Pottie,
• Abstract summary: We introduce a collaborative multi-agent framework as a novel method of incorporating inference-time into automatic question generation.<n>Preliminary evaluations show that this collaborative multi-agent framework elevates the quality of generated educational content.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Cognitively Diverse Multiple-Choice Question Generation: A Hybrid Multi-Agent Framework with Large Language Models [4.155649113742267]
  ReQUESTA is a hybrid, multi-agent framework for generating cognitively diverse multiple-choice questions (MCQs)<n>We evaluated the framework in a large-scale reading comprehension study using academic expository texts.<n>Results showed that ReQUESTA-generated items were consistently more challenging, more discriminative, and more strongly aligned with overall reading comprehension performance.
  arXiv  Detail & Related papers  (2026-02-03T16:26:47Z)
• A self-evolving multi-role collaborative framework with fine-grained difficulty guidance for innovative mathematical problem generation [3.4082981066509928]
  We propose the task of innovative math problem generation (IMPG)<n>This paper proposes a self-evolving, multi-role collaborative framework with fine-grained difficulty guidance.<n> Experiments show that, compared to baseline models, our proposed method significantly improves the innovation of the generated problems.
  arXiv  Detail & Related papers  (2026-01-16T21:36:04Z)
• EduAgentQG: A Multi-Agent Workflow Framework for Personalized Question Generation [56.43882334582494]
  We propose EduAgentQG, a multi-agent collaborative framework for generating high-quality and diverse personalized questions.<n>The framework consists of five specialized agents and operates through an iterative feedback loop.<n>EduAgentQG outperforms existing single-agent and multi-agent methods in terms of question diversity, goal consistency, and overall quality.
  arXiv  Detail & Related papers  (2025-11-08T12:25:31Z)
• Reinforcing Question Answering Agents with Minimalist Policy Gradient Optimization [80.09112808413133]
  Mujica is a planner that decomposes questions into acyclic graph of subquestions and a worker that resolves questions via retrieval and reasoning.<n>MyGO is a novel reinforcement learning method that replaces traditional policy updates with gradient Likelihood Maximum Estimation.<n> Empirical results across multiple datasets demonstrate the effectiveness of MujicaMyGO in enhancing multi-hop QA performance.
  arXiv  Detail & Related papers  (2025-05-20T18:33:03Z)
• Enabling Collaborative Parametric Knowledge Calibration for Retrieval-Augmented Vision Question Answering [16.14877145354785]
  Vision Question Answering (KB-VQA) systems address complex visual-grounded questions with knowledge retrieved from external knowledge bases.<n>We propose a unified retrieval-augmented VQA framework with collaborative parametric knowledge calibration.<n>Our approach achieves competitive performance against state-of-the-art models, delivering a significant 4.7% improvement in answering accuracy.
  arXiv  Detail & Related papers  (2025-04-05T05:42:12Z)
• Dual Ensembled Multiagent Q-Learning with Hypernet Regularizer [62.01554688056335]
  Overestimation in the multiagent setting has received comparatively little attention.<n>We propose a novel hypernet regularizer on hypernetwork weights and biases to constrain the optimization of online global Q-network to prevent overestimation accumulation.
  arXiv  Detail & Related papers  (2025-02-04T05:14:58Z)
• AQA: Adaptive Question Answering in a Society of LLMs via Contextual Multi-Armed Bandit [59.10281630985958]
  In question answering (QA), different questions can be effectively addressed with different answering strategies. We develop a dynamic method that adaptively selects the most suitable QA strategy for each question. Our experiments show that the proposed solution is viable for adaptive orchestration of a QA system with multiple modules.
  arXiv  Detail & Related papers  (2024-09-20T12:28:18Z)
• Automated Educational Question Generation at Different Bloom's Skill Levels using Large Language Models: Strategies and Evaluation [0.0]
  We examine the ability of five state-of-the-art large language models to generate diverse and high-quality questions of different cognitive levels. Our findings suggest that LLms can generate relevant and high-quality educational questions of different cognitive levels when prompted with adequate information.
  arXiv  Detail & Related papers  (2024-08-08T11:56:57Z)
• DuetRAG: Collaborative Retrieval-Augmented Generation [57.440772556318926]
  Collaborative Retrieval-Augmented Generation framework, DuetRAG, proposed. bootstrapping philosophy is to simultaneously integrate the domain fintuning and RAG models.
  arXiv  Detail & Related papers  (2024-05-12T09:48:28Z)
• ReST meets ReAct: Self-Improvement for Multi-Step Reasoning LLM Agent [50.508669199496474]
  We develop a ReAct-style LLM agent with the ability to reason and act upon external knowledge. We refine the agent through a ReST-like method that iteratively trains on previous trajectories. Starting from a prompted large model and after just two iterations of the algorithm, we can produce a fine-tuned small model.
  arXiv  Detail & Related papers  (2023-12-15T18:20:15Z)
• Retrieval-augmented Generation to Improve Math Question-Answering: Trade-offs Between Groundedness and Human Preference [0.0]
  We design prompts that retrieve and use content from a high-quality open-source math textbook to generate responses to real student questions. We evaluate the efficacy of this RAG system for middle-school algebra and geometry QA by administering a multi-condition survey. We argue that while RAG is able to improve response quality, designers of math QA systems must consider trade-offs between generating responses preferred by students and responses closely matched to specific educational resources.
  arXiv  Detail & Related papers  (2023-10-04T22:09:28Z)
• Complex QA and language models hybrid architectures, Survey [0.9242985360636448]
  This paper reviews the state-of-the-art of large language models (LLM) architectures and strategies for "complex" question-answering.
  arXiv  Detail & Related papers  (2023-02-17T18:31:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.