vix.ing · top · new · best · stats

Gala: Global LLM Agents for Text-to-Model Translation

2025/09/10 by Junyang Cai, Cai, Junyang, Serdar Kadıoğlu +3
Computer Science · #Class (philosophy) #Constraint (computer-aided design) #Constraint Satisfaction and Optimization #Constraint logic programming #Constraint programming #Multimodal Machine Learning Applications #Process (computing) #Task (project management) #Topic Modeling #Translation (biology)

paper · pdf · doi:10.48550/arxiv.2509.08970

published in arXiv (Cornell University) (Cornell University)

openalex publication_date 2025/09/10 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05

Abstract

Natural language descriptions of optimization or satisfaction problems are challenging to translate into correct MiniZinc models, as this process demands both logical reasoning and constraint programming expertise. We introduce Gala, a framework that addresses this challenge with a global agentic approach: multiple specialized large language model (LLM) agents decompose the modeling task by global constraint type. Each agent is dedicated to detecting and generating code for a specific class of global constraint, while a final assembler agent integrates these constraint snippets into a complete MiniZinc model. By dividing the problem into smaller, well-defined sub-tasks, each LLM handles a simpler reasoning challenge, potentially reducing overall complexity. We conduct initial experiments with several LLMs and show better performance against baselines such as one-shot prompting and chain-of-thought prompting. Finally, we outline a comprehensive roadmap for future work, highlighting potential enhancements and directions for improvement.

Citations

Related