# T2MM: An LLM Supported Architecture For Inquiry-Based Modeling

arXiv: https://arxiv.org/abs/2606.11210 · HTML: https://mlsanity.com/paper/2606.11210/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 24 references that are in the map.
- First posted on arXiv 24 Apr 2026.

## Builds on (most cited first, 8 of 8)

- [Beyond Final Answers: Evaluating Large Language Models for Math Tutoring](https://mlsanity.com/paper/2503.16460/) (2025)
- [Taking the Next Step with Generative Artificial Intelligence: The Transformative Role of Multimodal Large Language Models in Science Education](https://mlsanity.com/paper/2401.00832/) (2024)
- [Why LVLMs Are More Prone to Hallucinations in Longer Responses: The Role of Context](https://mlsanity.com/paper/2510.20229/) (2025)
- [MathViz-E: A Case-study in Domain-Specialized Tool-Using Agents](https://mlsanity.com/paper/2407.17544/) (2024)
- [Towards a Multimodal Document-grounded Conversational AI System for Education](https://mlsanity.com/paper/2504.13884/) (2025)
- [GenAI-DrawIO-Creator: A Framework for Automated Diagram Generation](https://mlsanity.com/paper/2601.05162/) (2026)
- [Cognitive Assistance for Inquiry-Based Modeling](https://mlsanity.com/paper/2209.02576/) (2022)
- [CogGen: A Learner-Centered Generative AI Architecture for Intelligent Tutoring with Programming Video](https://mlsanity.com/paper/2506.20600/) (2025)

## Abstract (arXiv)

Model Construction is a foundational practice in science learning that relies on visualization and interactivity. Large Language Models, increasingly augmented with multimodal capabilities, have been integrated in education contexts to support learning. However, these tools lack visual interactivity that is required by some learning contexts. We introduce Text to Multimodal Model (T2MM), a robust, dynamic LLM supported architecture that assists in model construction within the open inquiry ecology-based modeling software Virtual Experimental Research Assistant (VERA). T2MM accounts for the current context of the learner's model and creates interactive models, rather than static images, enabling the model to remain responsive to manual adjustment. To measure technical feasibility, we evaluate T2MM through a custom procedurally generated dataset of natural language learner modeling requests and target models within the VERA system. T2MM outperforms a baseline model generation architecture implemented through LLM-supported full code generation, common in the literature, across all measured success metrics. Our contribution not only outlines LLM integration into a inquiry-based learning modeling tool, but also describes a possible architecture through which more interactive multimodal LLM tools can be created.