Gala: 面向文本到模型转换的全局LLM智能体
Gala: Global LLM Agents for Text-to-Model Translation
AI总结：
针对自然语言转MiniZinc模型的难题，提出Gala全局智能体框架，通过多专用LLM智能体按约束类型分工建模、组装智能体整合代码的方式降低复杂度，实验显示其性能优于单次提示和思维链提示等基线，并规划了未来研究方向。
摘要：
将优化或可满足性问题的自然语言描述转换为正确的MiniZinc模型颇具挑战，因为该过程既需要逻辑推理能力，又要求具备约束编程专业知识。我们提出Gala框架，通过全局智能体方法应对这一挑战：多个专业化的大语言模型（LLM）智能体按全局约束类型分解建模任务。每个智能体专门负责检测某一特定类别的全局约束并生成对应代码，最终由一个组装智能体将这些约束代码片段整合为完整的MiniZinc模型。通过将问题拆分为更小、定义明确的子任务，每个LLM只需处理更简单的推理难题，有望降低整体复杂度。我们使用多款LLM开展了初步实验，结果表明其性能优于单次提示（one-shot prompting）和思维链提示（chain-of-thought prompting）等基线方法。最后，我们勾勒了未来工作的全面路线图，明确了潜在的增强方向与改进路径。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
