mlsanityData to 7 Oct 2026

EvoPrompt: Connecting LLMs with Evolutionary Algorithms Yields Powerful Prompt Optimizers

arXiv 2309.08532 ↗First posted 15 Sep 2023cs.CL cs.AIcited by 189

Not on the map. Why?

Cited by 29 in LLM agents and tool use, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Large Language Models (LLMs) excel in various tasks, but they rely on carefully crafted prompts that often demand substantial human effort. To automate this process, in this paper, we propose a novel framework for discrete prompt optimization, called EvoPrompt, which borrows the idea of evolutionary algorithms (EAs) as they exhibit good performance and fast convergence. To enable EAs to work on discrete prompts, which are natural language expressions that need to be coherent and human-readable, we connect LLMs with EAs. This approach allows us to simultaneously leverage the powerful language processing capabilities of LLMs and the efficient optimization performance of EAs. Specifically, abstaining from any gradients or parameters, EvoPrompt starts from a population of prompts and iteratively generates new prompts with LLMs based on the evolutionary operators, improving the population based on the development set. We optimize prompts for both closed- and open-source LLMs including GPT-3.5 and Alpaca, on 31 datasets covering language understanding, generation tasks, as well as BIG-Bench Hard (BBH) tasks. EvoPrompt significantly outperforms human-engineered prompts and existing methods for automatic prompt generation (e.g., up to 25% on BBH). Furthermore, EvoPrompt demonstrates that connecting LLMs with EAs creates synergies, which could inspire further research on the combination of LLMs and conventional algorithms.

Key facts. Cited by 189 papers in the map (data through 7 Oct 2026). Builds on 40 of its 72 references that are in the map. First posted on arXiv 15 Sep 2023.

Builds on

40 of 72 references.

References · 40

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2023GPT-4 Technical Reportcited by 18,132
  3. 2022Training language models to follow instructions with human feedbackcited by 15,712
  4. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  5. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  6. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,878
  7. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,769
  8. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,464
  9. 2015Character-level Convolutional Networks for Text Classificationcited by 2,293
  10. 2021Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processingcited by 2,222
  11. 2022Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Themcited by 1,767
  12. 2021Multitask Prompted Training Enables Zero-Shot Task Generalizationcited by 1,462
28 more
  1. 2022Large Language Models Are Human-Level Prompt Engineerscited by 1,020
  2. 2019How Can We Know What Language Models Know?cited by 953
  3. 2020Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inferencecited by 934
  4. 2021GPT Understands, Toocited by 715
  5. 2019Universal Adversarial Triggers for Attacking and Analyzing NLPcited by 709
  6. 2021Cross-Task Generalization via Natural Language Crowdsourcing Instructionscited by 696
  7. 2021P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Taskscited by 686
  8. 2023Automatic Prompt Optimization with "Gradient Descent" and Beam Searchcited by 628
  9. 2019SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarizationcited by 530
  10. 2023Is ChatGPT a General-Purpose Natural Language Processing Task Solver?cited by 486
  11. 2015Illuminating search spaces by mapping elitescited by 406
  12. 2022RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learningcited by 361
  13. 2022PromptSource: An Integrated Development Environment and Repository for Natural Language Promptscited by 288
  14. 2023Sentiment Analysis in the Era of Large Language Models: A Reality Checkcited by 262
  15. 2022OPT-IML: Scaling Language Model Instruction Meta Learning through the Lens of Generalizationcited by 235
  16. 2021Reframing Instructional Prompts to GPTk's Languagecited by 176
  17. 2022Evolution through Large Modelscited by 131
  18. 2023EvoPrompting: Language Models for Code-Level Neural Architecture Searchcited by 129
  19. 2022GrIPS: Gradient-free, Edit-based Instruction Search for Prompting Large Language Modelscited by 127
  20. 2023Language Model Crossover: Variation through Few-Shot Promptingcited by 119
  21. 2021Differentiable Prompt Makes Pre-trained Language Models Better Few-shot Learnerscited by 115
  22. 2023Chain-of-Thought Hub: A Continuous Effort to Measure Large Language Models' Reasoning Performancecited by 102
  23. 2020ASSET: A Dataset for Tuning and Evaluation of Sentence Simplification Models with Multiple Rewriting Transformationscited by 101
  24. 2023Can GPT-4 Perform Neural Architecture Search?cited by 74
  25. 2022Toward Human Readable Prompt Tuning: Kubrick's The Shining is a good movie, and a good prompt too?cited by 49
  26. 2023Multi-Task Instruction Tuning of LLaMa for Specific Scenarios: A Preliminary Study on Writing Assistancecited by 33
  27. 2023ChatGPT and Other Large Language Models as Evolutionary Engines for Online Interactive Collaborative Game Designcited by 20
  28. 2023Deliberate then Generate: Enhanced Prompting Framework for Text Generationcited by 13

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 12; 2024: 73; 2025: 43; 2026: 61.

189 papers.

Sort:

By area:

  1. 2023DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelinescited by 803
  2. 2023Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolutioncited by 521
  3. 2024Optimizing Instructions and Demonstrations for Multi-Stage Language Model Programscited by 270
  4. 2024Evolution of Heuristics: Towards Efficient Automatic Algorithm Design Using Large Language Modelcited by 258
  5. 2023Self-Taught Optimizer (STOP): Recursively Self-Improving Code Generationcited by 128
  6. 2024Attacks, Defenses and Evaluations for LLM Conversation Safety: A Surveycited by 124
  7. 2024LLM-SR: Scientific Equation Discovery via Programming with Large Language Modelscited by 117
  8. 2024EvoAgent: Towards Automatic Multi-Agent Generation via Evolutionary Algorithmscited by 109
  9. 2024LLMOPT: Learning to Define and Solve General Optimization Problems from Scratchcited by 102
  10. 2024Agent-Pro: Learning to Evolve via Policy-Level Reflection and Optimizationcited by 93
  11. 2024LLaMEA: A Large Language Model Evolutionary Algorithm for Automatically Generating Metaheuristicscited by 92
  12. 2024Evolutionary Computation in the Era of Large Language Model: Survey and Roadmapcited by 89
38 more
  1. 2024Coercing LLMs to do and reveal (almost) anythingcited by 88
  2. 2024Improving Text-to-Image Consistency via Automatic Prompt Optimizationcited by 88
  3. 2024Open-Endedness is Essential for Artificial Superhuman Intelligencecited by 79
  4. 2025Evolving Deeper LLM Thinkingcited by 58
  5. 2025EvoFlow: Evolving Diverse Agentic Workflows On The Flycited by 49
  6. 2024Efficient Prompting Methods for Large Language Models: A Surveycited by 46
  7. 2026AdaEvolve: Adaptive LLM Driven Zeroth-Order Optimizationcited by 46
  8. 2026EvoX: Meta-Evolution for Automated Discoverycited by 45
  9. 2024StreamBench: Towards Benchmarking Continuous Improvement of Language Agentscited by 44
  10. 2024A Comprehensive Study of Multimodal Large Language Models for Image Quality Assessmentcited by 43
  11. 2024Incremental Residual Concept Bottleneck Modelscited by 43
  12. 2024In-Context Principle Learning from Mistakescited by 42
  13. 2024Prompt Optimization with EASE? Efficient Ordering-aware Automated Selection of Exemplarscited by 37
  14. 2025Self-Supervised Prompt Optimizationcited by 37
  15. 2025CodeEvolve: an open source evolutionary coding agent for algorithmic discovery and optimizationcited by 37
  16. 2024Prompt Optimization with Human Feedbackcited by 35
  17. 2023Towards Optimizing with Large Language Modelscited by 34
  18. 2025EvoTest: Evolutionary Test-Time Learning for Self-Improving Agentic Systemscited by 34
  19. 2024Unleashing the Potential of Large Language Models as Prompt Optimizers: Analogical Analysis with Gradient-based Model Optimizerscited by 33
  20. 2025Meta-Reasoner: Dynamic Guidance for Optimized Inference-time Reasoning in Large Language Modelscited by 33
  21. 2024PromptWizard: Task-Aware Prompt Optimization Frameworkcited by 32
  22. 2024AI Safety in Generative AI Large Language Models: A Surveycited by 31
  23. 2025Language Models are Injective and Hence Invertiblecited by 31
  24. 2023Use Your INSTINCT: INSTruction optimization for LLMs usIng Neural bandits Coupled with Transformerscited by 29
  25. 2024Teach Better or Show Smarter? On Instructions and Exemplars in Automatic Prompt Optimizationcited by 28
  26. 2024On Discrete Prompt Optimization for Diffusion Modelscited by 28
  27. 2024Automatic Instruction Evolving for Large Language Modelscited by 24
  28. 2023Tailored Visions: Enhancing Text-to-Image Generation with Personalized Prompt Rewritingcited by 23
  29. 2024Toward Automated Algorithm Design: A Survey and Practical Guide to Meta-Black-Box-Optimizationcited by 23
  30. 2024REvolve: Reward Evolution with Large Language Models using Human Feedbackcited by 22
  31. 2024FunBO: Discovering Acquisition Functions for Bayesian Optimization with FunSearchcited by 22
  32. 2024Understanding the Importance of Evolutionary Search in Automated Heuristic Design with Large Language Modelscited by 22
  33. 2026From Static Templates to Dynamic Runtime Graphs: A Survey of Workflow Optimization for LLM Agentscited by 22
  34. 2024Scalable Reinforcement Post-Training Beyond Static Human Prompts: Evolving Alignment via Asymmetric Self-Playcited by 21
  35. 2025Searching for Privacy Risks in LLM Agents via Simulationcited by 19
  36. 2023Why Can Large Language Models Generate Correct Chain-of-Thoughts?cited by 16
  37. 2024Large Language Model-driven Meta-structure Discovery in Heterogeneous Information Networkcited by 16
  38. 2024StraGo: Harnessing Strategic Guidance for Prompt Optimizationcited by 16

50 most cited of 189 All 189 (JSON)