A Toolbox for Improving Evolutionary Prompt Search

2025/11/07 by Grießhaber, Daniel, Kimmich, Maximilian, Maucher, Johannes +1
Computer Science · Engineering · #Evolutionary Algorithms and Applications #Evolutionary algorithm #Evolutionary computation #Key (lock) #Optimization problem #Quality (philosophy) #Software Testing and Debugging Techniques #Toolbox #VLSI and FPGA Design Techniques

paper · open access · doi:10.48550/arxiv.2511.05120

published in arXiv (Cornell University) (Cornell University)

openalex publication_date 2025/11/07 · openalex created_date 2025/11/11 · openalex updated_date 2026/07/28

Abstract

Evolutionary prompt optimization has demonstrated effectiveness in refining prompts for LLMs. However, existing approaches lack robust operators and efficient evaluation mechanisms. In this work, we propose several key improvements to evolutionary prompt optimization that can partially generalize to prompt optimization in general: 1) decomposing evolution into distinct steps to enhance the evolution and its control, 2) introducing an LLM-based judge to verify the evolutions, 3) integrating human feedback to refine the evolutionary operator, and 4) developing more efficient evaluation strategies that maintain performance while reducing computational overhead. Our approach improves both optimization quality and efficiency. We release our code, enabling prompt optimization on new tasks and facilitating further research in this area.

Citations

• Automated Peer Reviewing in Paper SEA: Standardization, Evaluation, and Analysis
• Can large language models provide useful feedback on research papers? A large-scale empirical analysis
• Deliberate then Generate: Enhanced Prompting Framework for Text Generation
• Multi-Task Instruction Tuning of LLaMa for Specific Scenarios: A Preliminary Study on Writing Assistance
• EvoPrompting: Language Models for Code-Level Neural Architecture Search
• Language Model Crossover: Variation through Few-Shot Prompting
• Toward Human Readable Prompt Tuning: Kubrick's The Shining is a good movie, and a good prompt too?
• Large Language Models Are Human-Level Prompt Engineers
• RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning
• Training language models to follow instructions with human feedback
• Language Models are Few-Shot Learners
• EvoPrompt: Connecting LLMs with Evolutionary Algorithms Yields Powerful Prompt Optimizers

Related

• A Survey of Automatic Prompt Optimization with Instruction-focused Heuristic-based Search Algorithm
• GREATERPROMPT: A Unified, Customizable, and High-Performing Open-Source Toolkit for Prompt Optimization
• EvoPrompt: Connecting LLMs with Evolutionary Algorithms Yields Powerful Prompt Optimizers
• LLM Prompt Duel Optimizer: Efficient Label-Free Prompt Optimization
• GAAPO: Genetic Algorithmic Applied to Prompt Optimization