用多个专业AI代理协作，把自然语言转成精准的约束模型。
Gala: Global LLM Agents for Text-to-Model Translation
- 分角色分工：每个AI专注一类约束类型，降低理解难度。
- 实验显示优于单次提示和思维链提示，生成更准确的MiniZinc代码。
- 适合需要将问题描述转为可执行模型的研究者或工程师。
自然语言描述的优化或满足性问题难以准确转换为MiniZinc模型，因为该过程需要逻辑推理与约束编程知识。我们提出Gala框架，采用全局代理方法：多个专业大语言模型（LLM）代理按全局约束类型分解建模任务。每个代理负责检测并生成特定类别的全局约束代码，最终由一个集成代理将各约束片段组合成完整的MiniZinc模型。通过将任务拆分为更小、定义明确的子任务，每个LLM只需处理更简单的推理挑战，可能降低整体复杂度。我们在多个LLM上进行初步实验，结果表明其性能优于单次提示和思维链提示等基线方法。最后，我们提出未来工作的全面路线图，涵盖潜在改进方向与扩展路径。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。