用自然语言直接生成高效优化求解器，避免幻觉且无需反复测试
AutoSG: LLM-Driven Solver Generation Solely from Task Prompts for Expensive Optimization
- 通过检索文献确保代码真实可靠，杜绝领域知识幻觉
- 单步自优化保留关键结构，提升求解效率
- 无需实际运行即可快速评估，适合复杂优化任务
昂贵优化任务在现实应用中广泛存在，需要高度定制的求解器。尽管大模型驱动的自动化求解器生成具有潜力，但现有方法在处理昂贵优化时面临三大问题：因领域知识不足导致的事实性幻觉、精炼过程中破坏已有局部最优结构、以及在训练实例上执行带来的高昂评估成本和泛化受限。为此，我们提出 AutoSG，一种完全自动化的流程，可直接将自然语言提示转化为可执行的定制化求解器。AutoSG包含三项核心创新：基于检索增强的求解器生成模块，严格依据已验证文献生成代码；单步自精炼算子，在引入任务特异性改进的同时保留关键结构组件；基于无实例 Elo 的大模型作为裁判评估机制，实现快速全局排序。在多种昂贵优化任务上的广泛评估表明，AutoSG 显著优于人类设计的最先进框架及现有 LLM 生成求解器。
原文摘要 · Abstract (English)
Expensive optimization tasks are ubiquitous in real-world applications, demanding highly specialized solvers. While LLM-driven automated solver generation shows promise, current paradigms face three critical issues when tackling expensive optimization: factual hallucinations due to deficient domain knowledge, the frequent dismantling of previously established locally optimal structures during refinement, and the prohibitive evaluation costs alongside restricted generalization caused by executing on training instances. To address these issues, we introduce AutoSG, a fully automated workflow directly translating natural language prompts into executable customized solvers. AutoSG features three core innovations: a retrieval-augmented solver generation module strictly grounding code in verified literature; a one-step self-refinement operator introducing task-specific improvements while preserving critical structural components; and an instance-free Elo-based LLM-as-a-Judge evaluation mechanism rapidly establishing global rankings. Extensive evaluations across diverse expensive optimization tasks confirm AutoSG significantly outperforms human-designed state-of-the-art frameworks and existing LLM-generated solvers.
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。