A Survey of Automatic Prompt Engineering: An Optimization Perspective

2025/02/17 by Wenwu Li, Xiangfeng Wang, Li, Wenwu +5 · 19 citations
Computer Science · Engineering · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Low-power high-performance VLSI design #Machine Learning (cs.LG) #Numerical Methods and Algorithms

paper · pdf · doi:10.48550/arxiv.2502.11560

openalex publication_date 2025/02/17 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

The rise of foundation models has shifted focus from resource-intensive fine-tuning to prompt engineering, a paradigm that steers model behavior through input design rather than weight updates. While manual prompt engineering faces limitations in scalability, adaptability, and cross-modal alignment, automated methods, spanning foundation model (FM) based optimization, evolutionary methods, gradient-based optimization, and reinforcement learning, offer promising solutions. Existing surveys, however, remain fragmented across modalities and methodologies. This paper presents the first comprehensive survey on automated prompt engineering through a unified optimization-theoretic lens. We formalize prompt optimization as a maximization problem over discrete, continuous, and hybrid prompt spaces, systematically organizing methods by their optimization variables (instructions, soft prompts, exemplars), task-specific objectives, and computational frameworks. By bridging theoretical formulation with practical implementations across text, vision, and multimodal domains, this survey establishes a foundational framework for both researchers and practitioners, while highlighting underexplored frontiers in constrained optimization and agent-oriented prompt design.

Cited by

• Instruction-Tuning Open-Weight Language Models for BPMN Model Generation
• HiveMind: Contribution-Guided Online Prompt Optimization of LLM Multi-Agent Systems
• 2K-Characters-10K-Stories: A Quality-Gated Stylized Narrative Dataset with Disentangled Control and Sequence Consistency
• promptolution: A Unified, Modular Framework for Prompt Optimization
• Structured Prompting Enables More Robust Evaluation of Language Models
• Prompt-Based Value Steering of Large Language Models
• Prompt Optimization via Retrieved Reasoning Assets and Multi-Agent Analysis
• Are My Optimized Prompts Compromised? Exploring Vulnerabilities of LLM-based Optimizers
• Mathematics with large language models as provers and verifiers
• Multimodal Prompt Optimization: Why Not Leverage Multiple Modalities for MLLMs
• Reasoning-Aware Prompt Orchestration: A Foundation Model for Multi-Agent Language Model Coordination
• UniAPO: Unified Multimodal Automated Prompt Optimization
• Instance-level Randomization: Toward More Stable LLM Evaluations
• Parameter-Efficient Adaptation of mPLUG-Owl2 via Pixel-Level Visual Prompts for NR-IQA
• Transduction is All You Need for Structured Data Workflows
• APIO: Automatic Prompt Induction and Optimization for Grammatical Error Correction and Text Simplification
• LatentPrompt: Optimizing Promts in Latent Space
• Inverse Reinforcement Learning Meets Large Language Model Post-Training: Basics, Advances, and Opportunities
• Rethinking Prompt Optimization: Reinforcement, Diversification, and Migration in Blackbox LLMs

Related

• TAPO: Task-Referenced Adaptation for Prompt Optimization
• PromptWizard: Task-Aware Prompt Optimization Framework
• A Systematic Survey of Automatic Prompt Optimization Techniques
• SEE: Strategic Exploration and Exploitation for Cohesive In-Context Prompt Optimization
• iPrOp: Interactive Prompt Optimization for Large Language Models with a Human in the Loop