Automatic Prompt Optimization via Heuristic Search: A Survey

Recent advances in Large Language Models have led to remarkable achievements across a variety of Natural Language Processing tasks, making prompt engineering increasingly central to guiding model outputs. While manual methods can be effective, they typically rely on intuition and do not automatically refine prompts over time. In contrast, automatic prompt optimization employing heuristic-based search algorithms can systematically explore and improve prompts with minimal human oversight. This survey proposes a comprehensive taxonomy of these methods, categorizing them by where optimization occurs, what is optimized, what criteria drive the optimization, which operators generate new prompts, and which iterative search algorithms are applied. We further highlight specialized datasets and tools that support and accelerate automated prompt refinement. We conclude by discussing key open challenges pointing toward future opportunities for more robust and versatile LLM applications.

@article{cui2025_2502.18746,
  title={ Automatic Prompt Optimization via Heuristic Search: A Survey },
  author={ Wendi Cui and Jiaxin Zhang and Zhuohang Li and Hao Sun and Damien Lopez and Kamalika Das and Bradley A. Malin and Sricharan Kumar },
  journal={arXiv preprint arXiv:2502.18746},
  year={ 2025 }
}