HiFo-Prompt: Prompting with Hindsight and Foresight for LLM-based Automatic Heuristic Design
This work addresses a domain-specific problem in evolutionary computation for researchers and practitioners, offering an incremental improvement over existing LLM-based methods.
The paper tackled the problem of LLM-based Automatic Heuristic Design in Evolutionary Computation by introducing HiFo-Prompt, which uses foresight and hindsight prompting to improve search and knowledge accumulation, resulting in significantly higher-quality heuristics, faster convergence, and superior query efficiency compared to state-of-the-art methods.
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.