A Systematic Survey of Automatic Prompt Optimization Techniques

Since the advent of large language models (LLMs), prompt engineering has been a crucial step for eliciting desired responses for various Natural Language Processing (NLP) tasks. However, prompt engineering remains an impediment for end users due to rapid advances in models, tasks, and associated best practices. To mitigate this, Automatic Prompt Optimization (APO) techniques have recently emerged that use various automated techniques to help improve the performance of LLMs on various tasks. In this paper, we present a comprehensive survey summarizing the current progress and remaining challenges in this field. We provide a formal definition of APO, a 5-part unifying framework, and then proceed to rigorously categorize all relevant works based on their salient features therein. We hope to spur further research guided by our framework. Prompt optimization anatomy §2 Iteration depth §7 Variable steps §7.2 Fixed steps §7.1 Filter and retain promising candidates §6 Meta-heuristic ensemble §6.4 Region-based joint search §6.3 Upper confidence bound and variants §6.2 TopK Greedy Search §6.1 Candidate prompt generation §5 Program Synthesis §5.5 Coverage-based §5.4 Ensemble methods §5.4.3 Mixture of experts §5.4.2 Single prompt expansion §5.4.1 Metaprompt design §5.3