让大模型学会从经验中迭代优化启发式策略。
HiFo-Prompt: Prompting with Hindsight and Foresight for LLM-based Automatic Heuristic Design
- 用前瞻与回溯双重提示引导大模型动态调整搜索方向。
- 生成的启发式质量更高，收敛速度更快，节省大量查询次数。
- 适合研究进化计算与大模型协同设计的学者使用。
基于大模型的自动启发式设计（AHD）在进化计算（EC）框架中展现出良好前景，但受限于静态算子和缺乏知识积累机制。本文提出HiFo-Prompt框架，通过前瞻与回溯两种协同提示策略指导大模型：前瞻提示根据种群动态自适应调整搜索路径，平衡探索与利用；回溯提示则模仿人类专家，将过往代际中的成功启发式提炼为可复用的基础设计原则。该双机制将临时发现转化为持久知识库，使大模型能够基于自身经验持续学习。实验证明，HiFo-Prompt显著优于现有最先进方法，在生成更高质量启发式的同时实现更快收敛与更高查询效率。代码已开源：https://github.com/Challenger-XJTU/HiFo-Prompt。
原文摘要 · Abstract (English)
LLM-based Automatic Heuristic Design (AHD) within Evolutionary Computation (EC) frameworks has shown promising results. However, its effectiveness is hindered by the use of static operators and the lack of knowledge accumulation mechanisms. We introduce HiFo-Prompt, a framework that guides LLMs with two synergistic prompting strategies: Foresight and Hindsight. Foresight-based prompts adaptively steer the search based on population dynamics, managing the exploration-exploitation trade-off. In addition, hindsight-based prompts mimic human expertise by distilling successful heuristics from past generations into fundamental, reusable design principles. This dual mechanism transforms transient discoveries into a persistent knowledge base, enabling the LLM to learn from its own experience. Empirical results demonstrate that HiFo-Prompt significantly outperforms state-of-the-art LLM-based AHD methods, generating higher-quality heuristics while achieving substantially faster convergence and superior query efficiency. Our code is available at https://github.com/Challenger-XJTU/HiFo-Prompt.
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。