mlsanityData to 14 Oct 2026

A Survey of Automatic Prompt Optimization with Instruction-focused Heuristic-based Search Algorithm

arXiv 2502.18746 ↗First posted 26 Feb 2025cs.CLcited by 6

Not on the map. Why?

Abstract (arXiv)

Recent advances in Large Language Models have led to remarkable achievements across a variety of Natural Language Processing tasks, making prompt engineering increasingly central to guiding model outputs. While manual methods can be effective, they typically rely on intuition and do not automatically refine prompts over time. In contrast, automatic prompt optimization employing heuristic-based search algorithms can systematically explore and improve prompts with minimal human oversight. This survey proposes a comprehensive taxonomy of these methods, categorizing them by where optimization occurs, what is optimized, what criteria drive the optimization, which operators generate new prompts, and which iterative search algorithms are applied. We further highlight specialized datasets and tools that support and accelerate automated prompt refinement. We conclude by discussing key open challenges pointing toward future opportunities for more robust and versatile LLM applications.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 57 of its 83 references that are in the map. First posted on arXiv 26 Feb 2025.

Builds on

57 of 83 references.

References · 57

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  3. 2022Large Language Models are Zero-Shot Reasonerscited by 4,374
  4. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  5. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,915
  6. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  7. 2023Universal and Transferable Adversarial Attacks on Aligned Language Modelscited by 3,104
  8. 2018Neural Tangent Kernel: Convergence and Generalization in Neural Networkscited by 2,621
  9. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,592
  10. 2022Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Themcited by 1,807
  11. 2020Making Pre-trained Language Models Better Few-shot Learnerscited by 1,256
  12. 2022Large Language Models Are Human-Level Prompt Engineerscited by 1,045
38 more
  1. 2023DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelinescited by 832
  2. 2023Automatic Prompt Optimization with "Gradient Descent" and Beam Searchcited by 653
  3. 2023Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolutioncited by 551
  4. 2023Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyondcited by 411
  5. 2022RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learningcited by 366
  6. 2017"Liar, Liar Pants on Fire": A New Benchmark Dataset for Fake News Detectioncited by 363
  7. 2023Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discoverycited by 336
  8. 2024Optimizing Instructions and Demonstrations for Multi-Stage Language Model Programscited by 291
  9. 2022Black-Box Tuning for Language-Model-as-a-Servicecited by 256
  10. 2023PromptAgent: Strategic Planning with Language Models Enables Expert-level Prompt Optimizationcited by 233
  11. 2024Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attackscited by 156
  12. 2022Instruction Induction: From Few Examples to Natural Language Task Descriptionscited by 152
  13. 2021OpenPrompt: An Open-source Framework for Prompt-learningcited by 148
  14. 2023Black-Box Prompt Optimization: Aligning Large Language Models without Model Trainingcited by 122
  15. 2023SAC3: Reliable Hallucination Detection in Black-Box Language Models via Semantic-aware Cross-check Consistencycited by 90
  16. 2024Fine-Tuning and Prompt Optimization: Two Great Steps that Work Better Togethercited by 40
  17. 2023Query-Dependent Prompt Evaluation and Optimization with Offline Inverse RLcited by 37
  18. 2024Efficient Prompt Optimization Through the Lens of Best Arm Identificationcited by 37
  19. 2024Accelerating Greedy Coordinate Gradient and General Prompt Optimization via Probe Samplingcited by 37
  20. 2024Prompt Optimization with EASE? Efficient Ordering-aware Automated Selection of Exemplarscited by 37
  21. 2022PromptBoosting: Black-Box Text Classification with Ten Forward Passescited by 36
  22. 2024Unleashing the Potential of Large Language Models as Prompt Optimizers: Analogical Analysis with Gradient-based Model Optimizerscited by 35
  23. 2023Prompt Optimization via Adversarial In-Context Learningcited by 33
  24. 2023Joint Prompt Optimization of Stacked LLMs using Variational Inferencecited by 32
  25. 2024PRompt Optimization in Multi-Step Tasks (PROMST): Integrating Human Feedback and Heuristic-based Samplingcited by 32
  26. 2023AutoHint: Automatic Prompt Optimization with Hint Generationcited by 30
  27. 2023Use Your INSTINCT: INSTruction optimization for LLMs usIng Neural bandits Coupled with Transformerscited by 30
  28. 2024Teach Better or Show Smarter? On Instructions and Exemplars in Automatic Prompt Optimizationcited by 29
  29. 2024On Discrete Prompt Optimization for Diffusion Modelscited by 29
  30. 2024SPRIG: Improving Large Language Model Performance by System Prompt Optimizationcited by 29
  31. 2023PREFER: Prompt Ensemble Learning via Feedback-Reflect-Refinecited by 28
  32. 2024APEER: Automatic Prompt Engineering Enhances Large Language Model Rerankingcited by 28
  33. 2024Task Facet Learning: A Structured Approach to Prompt Optimizationcited by 19
  34. 2024Efficient and Accurate Prompt Optimization: the Benefit of Memory in Exemplar-Guided Reflectioncited by 18
  35. 2023InstOptima: Evolutionary Multi-objective Instruction Optimization via Large Language Model-based Instruction Operatorscited by 17
  36. 2024One Prompt is not Enough: Automated Construction of a Mixture-of-Expert Promptscited by 16
  37. 2023SPELL: Semantic Prompt Evolution based on a LLMcited by 15
  38. 2024AMPO: Automatic Multi-Branched Prompt Optimizationcited by 11

50 most cited of 57 All 57 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 3.

6 papers.

  1. 2026MASPO: Joint Prompt Optimization for LLM-based Multi-Agent Systemscited by 7
  2. 2025TextBO: Bayesian Optimization in Language Space for Eval-Efficient Self-Improving AIcited by 3
  3. 2025SCE: Scalable Consistency Ensembles Make Blackbox Large Language Model Generation More Reliablecited by 1
  4. 2025LatentPrompt: Optimizing Promts in Latent Spacecited by 1
  5. 2026Prompting Policies for Multi-step Reasoning and Tool-Use in Black-box LLMs with Iterative Distillation of Experiencecited by 0
  6. 2026KG-FairDiff: Knowledge Graph-Guided Prompt Refinement for Demographically Fair Text-to-Image Generationcited by 0