Gala: Global LLM Agents for Text-to-Model Translation
This addresses the problem of automating constraint modeling for users without programming expertise, but it appears incremental as it builds on existing LLM methods with a multi-agent approach.
The paper tackles the challenge of translating natural language descriptions of optimization problems into correct MiniZinc models by introducing Gala, a framework that uses multiple specialized LLM agents to decompose the task by constraint type, and shows better performance against baselines like one-shot and chain-of-thought prompting in initial experiments.
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.