# Text2Model: Modeling Copilots for Text-to-Model Translation

arXiv: https://arxiv.org/abs/2604.12955 · HTML: https://mlsanity.com/paper/2604.12955/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 59 references that are in the map.
- First posted on arXiv 14 Apr 2026.

## Builds on (most cited first, 26 of 26)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning](https://mlsanity.com/paper/1709.00103/) (2017)
- [Unifying Large Language Models and Knowledge Graphs: A Roadmap](https://mlsanity.com/paper/2306.08302/) (2023)
- [Efficient Guided Generation for Large Language Models](https://mlsanity.com/paper/2307.09702/) (2023)
- [Structured Chain-of-Thought Prompting for Code Generation](https://mlsanity.com/paper/2305.06599/) (2023)
- [NL4Opt Competition: Formulating Optimization Problems Based on Their Natural Language Descriptions](https://mlsanity.com/paper/2303.08233/) (2023)
- [ORLM: A Customizable Framework in Training Large Models for Automated Optimization Modeling](https://mlsanity.com/paper/2405.17743/) (2024)
- [Chain of Code: Reasoning with a Language Model-Augmented Code Emulator](https://mlsanity.com/paper/2312.04474/) (2023)
- [LLMOPT: Learning to Define and Solve General Optimization Problems from Scratch](https://mlsanity.com/paper/2410.13213/) (2024)
- [Augmenting Operations Research with Auto-Formulation of Optimization Models from Problem Descriptions](https://mlsanity.com/paper/2209.15565/) (2022)
- [SeqZero: Few-shot Compositional Semantic Parsing with Sequential Prompts and Zero-shot Models](https://mlsanity.com/paper/2205.07381/) (2022)
- [OptiMUS-0.3: Using Large Language Models to Model and Solve Optimization Problems at Scale](https://mlsanity.com/paper/2407.19633/) (2024)
- [Validating Large Language Models with ReLM](https://mlsanity.com/paper/2211.15458/) (2022)
- [Planetarium: A Rigorous Benchmark for Translating Text to Structured Planning Languages](https://mlsanity.com/paper/2407.03321/) (2024)
- [Incorporating Commonsense Knowledge Graph in Pretrained Models for Social Commonsense Tasks](https://mlsanity.com/paper/2105.05457/) (2021)
- ["I Want It That Way": Enabling Interactive Decision Support Using Large Language Models and Constraint Programming](https://mlsanity.com/paper/2312.06908/) (2023)
- [Synthesizing mixed-integer linear programming models from natural language descriptions](https://mlsanity.com/paper/2311.15271/) (2023)
- [Large-Scale Optimization Model Auto-Formulation: Harnessing LLM Flexibility via Structured Workflow](https://mlsanity.com/paper/2601.09635/) (2026)
- [OptiMind: Teaching LLMs to Think Like Optimization Experts](https://mlsanity.com/paper/2509.22979/) (2025)
- [Logic.py: Bridging the Gap between LLMs and Constraint Solvers](https://mlsanity.com/paper/2502.15776/) (2025)
- [Combining Constraint Programming Reasoning with Large Language Model Predictions](https://mlsanity.com/paper/2407.13490/) (2024)
- [PubGraph: A Large-Scale Scientific Knowledge Graph](https://mlsanity.com/paper/2302.02231/) (2023)
- [DualSchool: How Reliable are LLMs for Optimization Education?](https://mlsanity.com/paper/2505.21775/) (2025)
- [Domain Adaptable Prescriptive AI Agent for Enterprise](https://mlsanity.com/paper/2407.20447/) (2024)
- [Extracting Problem Structure with LLMs for Optimized SAT Local Search](https://mlsanity.com/paper/2501.14630/) (2025)
- [Gala: Global LLM Agents for Text-to-Model Translation](https://mlsanity.com/paper/2509.08970/) (2025)

## Abstract (arXiv)

There is growing interest in leveraging large language models (LLMs) for text-to-model translation and optimization tasks. This paper aims to advance this line of research by introducing textscText2Model and textscText2Zinc. textscText2Model is a suite of copilots based on several LLM strategies with varying complexity, along with an online leaderboard. textscText2Zinc is a cross-domain dataset for capturing optimization and satisfaction problems specified in natural language, along with an interactive editor with built-in AI assistant. While there is an emerging literature on using LLMs for translating combinatorial problems into formal models, our work is the first attempt to integrate textitboth satisfaction and optimization problems within a textitunified architecture and textitdataset. Moreover, our approach is textitsolver-agnostic unlike existing work that focuses on translation to a solver-specific model. To achieve this, we leverage textscMiniZinc's solver-and-paradigm-agnostic modeling capabilities to formulate combinatorial problems. We conduct comprehensive experiments to compare execution and solution accuracy across several single- and multi-call strategies, including; zero-shot prompting, chain-of-thought reasoning, intermediate representations via knowledge-graphs, grammar-based syntax encoding, and agentic approaches that decompose the model into sequential sub-tasks. Our copilot strategies are competitive, and in parts improve, recent research in this domain. Our findings indicate that while LLMs are promising they are not yet a push-button technology for combinatorial modeling. We contribute textscText2Model copilots and leaderboard, and textscText2Zinc and interactive editor to open-source to support closing this performance gap.