LACE：用大语言模型发现互补启发式算法求解组合优化问题
摘要
Huatian Gong 等人在 Nature Machine Intelligence 发表 LACE，一个基于大语言模型的优化算法设计框架。该框架先构建经过验证的问题契约，再演化出一组互补的启发式算法，共同求解单一方法无法处理的问题。论文于 2026 年 10 月 1 日在线发表，DOI 为 10.1038/s42256-026-01307-8。
摘要由模型根据原文撰写，以原文为准。
正文 · 原文
Nature Machine Intelligence, Published online: 01 October 2026; doi:10.1038/s42256-026-01307-8
Huatian Gong and colleagues developed LACE, a large language model-based framework that designs optimization algorithms. It builds a verified problem contract, then evolves a portfolio of complementary heuristics that together solve problems that no single method can handle.
注意转载授权 · 阅读原文
来源：Nature Machine Intelligence · nature.com
引用原文
Huatian Gong. Large language models discover complementary heuristics for combinatorial optimization[EB/OL]. (2026-10-01)[访问日期]. https://www.nature.com/articles/s42256-026-01307-8.