A Survey of Automatic Prompt Engineering: An Optimization Perspective

📅 2025-02-17
📈 Citations: 0
Influential: 0
📄 PDF

career value

211K/year
🤖 AI Summary
This paper addresses the lack of a systematic theoretical framework for automated prompt engineering by proposing the first unified optimization-theoretic survey across modalities. It formalizes discrete, continuous, and hybrid prompt variables—including instructions, soft prompts, and in-context examples—as constrained optimization problems, applicable to text, vision, and multimodal tasks. Methodologically, it integrates gradient-based optimization, evolutionary algorithms, and reinforcement learning to enable end-to-end, objective-driven prompt generation. Key contributions are: (1) the first optimization-theory-driven taxonomic framework for cross-modal prompt engineering; (2) the explicit identification and delineation of two frontier directions—constrained optimization and agent-oriented prompt design; and (3) a comprehensive knowledge system spanning the full technical spectrum and application domains of automated prompt engineering, providing a scalable theoretical foundation and methodological guidance for both research and practice.

Technology Category

Application Category

📝 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.
Problem

Research questions and friction points this paper is trying to address.

Automated prompt engineering methods
Optimization across diverse prompt spaces
Unified framework for multimodal applications
Innovation

Methods, ideas, or system contributions that make the work stand out.

Automated prompt engineering methods
Optimization over diverse prompt spaces
Unified framework for multimodal domains
🔎 Similar Papers
No similar papers found.
W
Wenwu Li
School of Computer Science and Technology, Tongji University
X
Xiangfeng Wang
Key Laboratory of Mathematics and Engineering Applications, MoE, East China Normal University; School of Computer Science and Technology, East China Normal University
W
Wenhao Li
School of Computer Science and Technology, Tongji University
B
Bo Jin
Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University; School of Computer Science and Technology, Tongji University