Exploring Agentic Workflows for Generating High Quality Math Visual Aids

• URL: http://arxiv.org/abs/2607.09839v1
• Date: Fri, 10 Jul 2026 17:12:38 GMT
• Title: Exploring Agentic Workflows for Generating High Quality Math Visual Aids
• Abstract summary: We introduce an agentic workflow that enables Large Language Models (LLMs) to evaluate the quality of generated visuals.<n>This self improvement loop aims to enhance the accuracy and educational appropriateness of AI generated diagrams.
• Score: 0.8228126670075446
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Mathematical diagrams play a crucial role in K 12 education, both as problem components and as scaffolding for student comprehension. However, current AI tools, including Large Language Models (LLMs), struggle to reliably generate accurate and pedagogically sound visual diagrams, even when provided with detailed descriptions. A significant gap therefore remains in the reliable generation of diagrams for middle school mathematics. To address this, we introduce an agentic workflow that enables LLM agents to evaluate the quality of generated visuals and use this feedback to iteratively improve their outputs. This self improvement loop aims to enhance the accuracy and educational appropriateness of AI generated diagrams. Our research investigates two questions. First, can LLMs accurately generate quality assurance questions for a visual aid given specific criteria for visual quality? Second, given valid quality assurance questions, can Vision Language Models effectively evaluate generated K 12 visual aids and use the resulting feedback to improve them iteratively? We conduct an exploratory evaluation of our agentic workflow and identify key areas for improvement, including stronger spatial reasoning and more comprehensive coverage of diagram features in the generated quality assurance questions. Our results provide preliminary evidence that this approach can improve the reliability and educational value of AI generated mathematical diagrams.

Related papers

• CV-Arena: An Open Benchmark for Instructional Computer Vision Problem Solving with Human-AI Collaborative Preferences [51.86576932800981]
  We introduce CV-Arena, an open benchmark designed to evaluate this capability at professional scales.<n>CV-Arena contains 12K high-resolution real-image instruction pairs spanning 16 instruction-based visual task types.<n>We develop CV-Agent, a lightweight agentic model that combines planning, editing, and verification.
  arXiv  Detail & Related papers  (2026-05-30T23:37:55Z)
• Can We Improve Educational Diagram Generation with In-Context Examples? Not if a Hallucination Spoils the Bunch [3.430175346274554]
  This study introduces a novel method for diagram code generation with in-context examples based on the Rhetorical Structure Theory (RST)<n>Our approach is evaluated by computer science educators, who assessed 150 diagrams generated with large language models (LLMs) for logical organization, connectivity, layout aesthetic, and AI hallucination.
  arXiv  Detail & Related papers  (2026-01-28T10:45:28Z)
• QualiRAG: Retrieval-Augmented Generation for Visual Quality Understanding [80.66379018208568]
  Visual quality assessment is shifting from prediction to interpretable quality understanding.<n>Current approaches rely on supervised fine-tuning or reinforcement learning on curated instruction.<n>We propose VbfQualiRAG, a framework that systematically leverages latent perceptual knowledge of large multimodal models for visual quality perception.
  arXiv  Detail & Related papers  (2026-01-26T06:27:03Z)
• Q-REAL: Towards Realism and Plausibility Evaluation for AI-Generated Content [71.46991494014382]
  We introduce Q-Real, a novel dataset for fine-grained evaluation of realism and plausibility in AI-generated images.<n>Q-Real consists of 3,088 images generated by popular text-to-image models.<n>We construct Q-Real Bench to evaluate them on two tasks: judgment and grounding with reasoning.
  arXiv  Detail & Related papers  (2025-11-21T02:43:17Z)
• VisualQuality-R1: Reasoning-Induced Image Quality Assessment via Reinforcement Learning to Rank [30.316630325648834]
  We introduce VisualQuality-R1, a reasoning-induced no-reference IQA (NR-IQA) model, and we train it with reinforcement learning to rank.<n>We show that VisualQuality-R1 consistently outperforms discriminative deep learning-based NR-IQA models.<n>VisualQuality-R1 is capable of generating contextually rich, human-aligned quality descriptions.
  arXiv  Detail & Related papers  (2025-05-20T14:56:50Z)
• Towards Efficient Educational Chatbots: Benchmarking RAG Frameworks [2.362412515574206]
  Large Language Models (LLMs) have proven immensely beneficial in education by capturing vast amounts of literature-based information.<n>We propose a generative AI-powered GATE question-answering framework that leverages LLMs to explain GATE solutions and support students in their exam preparation.
  arXiv  Detail & Related papers  (2025-03-02T08:11:07Z)
• Self-Evolving Critique Abilities in Large Language Models [59.861013614500024]
  This paper explores enhancing critique abilities of Large Language Models (LLMs)<n>We introduce SCRIT, a framework that trains LLMs with self-generated data to evolve their critique abilities.<n>Our analysis reveals that SCRIT's performance scales positively with data and model size.
  arXiv  Detail & Related papers  (2025-01-10T05:51:52Z)
• Multi-Modal Prompt Learning on Blind Image Quality Assessment [65.0676908930946]
  Image Quality Assessment (IQA) models benefit significantly from semantic information, which allows them to treat different types of objects distinctly. Traditional methods, hindered by a lack of sufficiently annotated data, have employed the CLIP image-text pretraining model as their backbone to gain semantic awareness. Recent approaches have attempted to address this mismatch using prompt technology, but these solutions have shortcomings. This paper introduces an innovative multi-modal prompt-based methodology for IQA.
  arXiv  Detail & Related papers  (2024-04-23T11:45:32Z)
• CogCoM: A Visual Language Model with Chain-of-Manipulations Reasoning [61.21923643289266]
  Chain of Manipulations is a mechanism that enables Vision-Language Models to solve problems step-by-step with evidence.<n>After training, models can solve various visual problems by eliciting intrinsic manipulations (e.g., grounding, zoom in) actively without involving external tools.<n>Our trained model, textbfCogCoM, achieves state-of-the-art performance across 9 benchmarks from 4 categories.
  arXiv  Detail & Related papers  (2024-02-06T18:43:48Z)

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.