Modeling Co-Pilots for Text-to-Model Translation

2026-04-14

AI Summary

This work proposes a unified large language model (LLM)-based framework that automatically translates natural language descriptions of combinatorial optimization and constraint satisfaction problems into solver-agnostic formal models. By introducing the Text2Model suite of collaborative agents and Text2Zinc—the first cross-domain dataset encompassing both optimization and satisfaction tasks—the approach integrates zero-shot prompting, chain-of-thought reasoning, knowledge graph-based intermediate representations, and task decomposition to enable efficient modeling. Implemented on the MiniZinc platform with support for multiple solvers, the method significantly advances modeling automation, achieving solution accuracy and execution efficiency comparable to or better than existing approaches. The results demonstrate both the promise and limitations of LLMs in combinatorial modeling. An interactive editor and an online leaderboard have been open-sourced to foster further research.

Technology Category

• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories
• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

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 \textsc{Text2Model} and \textsc{Text2Zinc}. \textsc{Text2Model} is a suite of co-pilots based on several LLM strategies with varying complexity, along with an online leaderboard. \textsc{Text2Zinc} 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 \textit{both} satisfaction and optimization problems within a \textit{unified architecture} and \textit{dataset}. Moreover, our approach is \textit{solver-agnostic} unlike existing work that focuses on translation to a solver-specific model. To achieve this, we leverage \textsc{MiniZinc}'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 co-pilot 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 \textsc{Text2Model} co-pilots and leaderboard, and \textsc{Text2Zinc} and interactive editor to open-source to support closing this performance gap.

Problem

• text-to-model translation
• combinatorial modeling
• optimization problems
• satisfaction problems
• solver-agnostic

Innovation

• text-to-model translation
• solver-agnostic modeling
• unified architecture
• combinatorial optimization
• large language models