mlsanityData to 14 Oct 2026

Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution

arXiv 2309.16797 ↗First posted 28 Sep 2023cs.CL cs.AI cs.LGcited by 551

On the map: LLM reasoning → Prompting and chain-of-thought reasoning

also in 1 more
Abstract (arXiv)

Popular prompt strategies like Chain-of-Thought Prompting can dramatically improve the reasoning abilities of Large Language Models (LLMs) in various domains. However, such hand-crafted prompt-strategies are often sub-optimal. In this paper, we present Promptbreeder, a general-purpose self-referential self-improvement mechanism that evolves and adapts prompts for a given domain. Driven by an LLM, Promptbreeder mutates a population of task-prompts, and subsequently evaluates them for fitness on a training set. Crucially, the mutation of these task-prompts is governed by mutation-prompts that the LLM generates and improves throughout evolution in a self-referential way. That is, Promptbreeder is not just improving task-prompts, but it is also improving the mutationprompts that improve these task-prompts. Promptbreeder outperforms state-of-the-art prompt strategies such as Chain-of-Thought and Plan-and-Solve Prompting on commonly used arithmetic and commonsense reasoning benchmarks. Furthermore, Promptbreeder is able to evolve intricate task-prompts for the challenging problem of hate speech classification.

Key facts. Cited by 551 papers in the map (data through 14 Oct 2026). Placed in Prompting and chain-of-thought reasoning, one of 17 directions in LLM reasoning. Builds on 57 of its 73 references that are in the map. First posted on arXiv 28 Sep 2023.

Builds on

57 of 73 references.

Closest ancestors · 10

Same direction, newest first

  1. 2023Graph of Thoughts: Solving Elaborate Problems with Large Language Models18 Aug
  2. 2023Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models6 May
  3. 2023Automatic Prompt Augmentation and Selection with Chain-of-Thought from Labeled Data24 Feb
  4. 2022Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks22 Nov
  5. 2022Automatic Chain of Thought Prompting in Large Language Models7 Oct
  6. 2022Text and Patterns: For Effective Chain of Thought, It Takes Two to Tango16 Sep
  7. 2022Large Language Models are Zero-Shot Reasoners24 May
  8. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Models21 May
  9. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Models21 Mar
  10. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Models28 Jan

Other references · 47

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  4. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  5. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
  6. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,795
  7. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
  8. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  9. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,442
  10. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,211
  11. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,724
  12. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,191
35 more
  1. 2018CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledgecited by 1,822
  2. 2021Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivitycited by 1,135
  3. 2022Large Language Models Are Human-Level Prompt Engineerscited by 1,045
  4. 2022STaR: Bootstrapping Reasoning With Reasoningcited by 940
  5. 2021Show Your Work: Scratchpads for Intermediate Computation with Language Modelscited by 886
  6. 2021Are NLP Models really able to Solve Simple Math Word Problems?cited by 878
  7. 2023Large Language Models as Optimizerscited by 864
  8. 2021Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategiescited by 743
  9. 2023Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizescited by 737
  10. 2022Large Language Models Can Self-Improvecited by 664
  11. 2023Automatic Prompt Optimization with "Gradient Descent" and Beam Searchcited by 653
  12. 2017Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problemscited by 650
  13. 2023MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Actioncited by 517
  14. 2015Illuminating search spaces by mapping elitescited by 425
  15. 2016Reinforcement Learning with Unsupervised Auxiliary Taskscited by 404
  16. 2023Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agentscited by 398
  17. 2021Learning How to Ask: Querying LMs with Mixtures of Soft Promptscited by 377
  18. 2017Population Based Training of Neural Networkscited by 367
  19. 2016Solving General Arithmetic Word Problemscited by 360
  20. 2020Prioritized Level Replaycited by 198
  21. 2023EvoPrompt: Connecting LLMs with Evolutionary Algorithms Yields Powerful Prompt Optimizerscited by 193
  22. 2022Evolving Curricula with Regret-Based Environment Designcited by 173
  23. 2022Instruction Induction: From Few Examples to Natural Language Task Descriptionscited by 152
  24. 2022Evolution through Large Modelscited by 134
  25. 2023EvoPrompting: Language Models for Code-Level Neural Architecture Searchcited by 131
  26. 2023Language Model Crossover: Variation through Few-Shot Promptingcited by 122
  27. 2021Replay-Guided Adversarial Environment Designcited by 111
  28. 2021Evaluating the Robustness of Neural Language Models to Input Perturbationscited by 87
  29. 2023OMNI: Open-endedness via Models of human Notions of Interestingnesscited by 70
  30. 2020ETHOS: an Online Hate Speech Detection Datasetcited by 66
  31. 2022A Modern Self-Referential Weight Matrix That Learns to Modify Itselfcited by 41
  32. 2022General Intelligence Requires Rethinking Explorationcited by 20
  33. 2022Eliminating Meta Optimization Through Self-Referential Meta Learningcited by 14
  34. 2023SPRING: Studying the Paper and Reasoning to Play Gamescited by 11
  35. 2019Evolvability ES: Scalable and Direct Optimization of Evolvabilitycited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 15; 2024: 96; 2025: 152; 2026: 288.

551 papers.

Sort:

By area:

  1. 2025AlphaEvolve: A coding agent for scientific and algorithmic discoverycited by 867
  2. 2024AFlow: Automating Agentic Workflow Generationcited by 432
  3. 2024Automated Design of Agentic Systemscited by 407
  4. 2023Can Generalist Foundation Models Outcompete Special-Purpose Tuning? Case Study in Medicinecited by 329
  5. 2025Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Modelscited by 293
  6. 2024Optimizing Instructions and Demonstrations for Multi-Stage Language Model Programscited by 291
  7. 2024Evolution of Heuristics: Towards Efficient Automatic Algorithm Design Using Large Language Modelcited by 268
  8. 2023PromptAgent: Strategic Planning with Language Models Enables Expert-level Prompt Optimizationcited by 233
  9. 2024Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Promptscited by 205
  10. 2025Multi-agent Architecture Search via Agentic Supernetcited by 179
  11. 2025A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligencecited by 170
  12. 2024AgentSquare: Automatic LLM Agent Search in Modular Design Spacecited by 155
38 more
  1. 2023Self-Taught Optimizer (STOP): Recursively Self-Improving Code Generationcited by 148
  2. 2024BALROG: Benchmarking Agentic LLM and VLM Reasoning On Gamescited by 146
  3. 2024Who Validates the Validators? Aligning LLM-Assisted Evaluation of LLM Outputs with Human Preferencescited by 144
  4. 2025Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systemscited by 126
  5. 2024Empowering Biomedical Discovery with AI Agentscited by 118
  6. 2024Self-Discover: Large Language Models Self-Compose Reasoning Structurescited by 110
  7. 2025Agentic Large Language Models, a surveycited by 108
  8. 2024A Survey on Self-Evolution of Large Language Modelscited by 91
  9. 2024Evolutionary Computation in the Era of Large Language Model: Survey and Roadmapcited by 90
  10. 2024Improving Text-to-Image Consistency via Automatic Prompt Optimizationcited by 90
  11. 2025AgentNet: Decentralized Evolutionary Coordination for LLM-based Multi-Agent Systemscited by 90
  12. 2024Language Agents as Optimizable Graphscited by 89
  13. 2024Open-Endedness is Essential for Artificial Superhuman Intelligencecited by 80
  14. 2025A Self-Improving Coding Agentcited by 79
  15. 2025ThetaEvolve: Test-time Learning on Open Problemscited by 64
  16. 2025A Systematic Survey of Automatic Prompt Optimization Techniquescited by 63
  17. 2025FlowReasoner: Reinforcing Query-Level Meta-Agentscited by 63
  18. 2024Efficient Evolutionary Search Over Chemical Space with Large Language Modelscited by 61
  19. 2026AdaEvolve: Adaptive LLM Driven Zeroth-Order Optimizationcited by 60
  20. 2026EvoX: Meta-Evolution for Automated Discoverycited by 60
  21. 2025Evolving Deeper LLM Thinkingcited by 58
  22. 2025ScoreFlow: Mastering LLM Agent Workflows via Score-based Preference Optimizationcited by 56
  23. 2023A Setwise Approach for Effective and Highly Efficient Zero-shot Ranking with Large Language Modelscited by 55
  24. 2025EvoFlow: Evolving Diverse Agentic Workflows On The Flycited by 55
  25. 2023Prompt Engineering a Prompt Engineercited by 53
  26. 2025MARFT: Multi-Agent Reinforcement Fine-Tuningcited by 52
  27. 2024Internal Consistency and Self-Feedback in Large Language Models: A Surveycited by 50
  28. 2024Optimized Feature Generation for Tabular Data via LLMs with Decision Tree Reasoningcited by 49
  29. 2024Efficient Prompting Methods for Large Language Models: A Surveycited by 47
  30. 2024Large Language Models Can Solve Real-World Planning Rigorously with Formal Verification Toolscited by 47
  31. 2026HarnessX: A Composable, Adaptive, and Evolvable Agent Harness Foundrycited by 47
  32. 2024PRewrite: Prompt Rewriting with Reinforcement Learningcited by 45
  33. 2024Evolving Code with A Large Language Modelcited by 43
  34. 2025Language Self-Play For Data-Free Trainingcited by 43
  35. 2025ChemAgent: Self-updating Library in Large Language Models Improves Chemical Reasoningcited by 41
  36. 2024CodecLM: Aligning Language Models with Tailored Synthetic Datacited by 39
  37. 2023MechGPT, a language-based strategy for mechanics and materials modeling that connects knowledge across scales, disciplines and modalitiescited by 38
  38. 2024In-context learning enables multimodal large language models to classify cancer pathology imagescited by 38

50 most cited of 551 All 551 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024Auto-Evolve: Enhancing Large Language Model's Performance via Self-Reasoning Framework
  2. 2025How to Auto-optimize Prompts for Domain Tasks? Adaptive Prompting and Reasoning through Evolutionary Domain Knowledge Adaptation
  3. 2025Evolving Prompts In-Context: An Open-ended, Self-replicating Perspective
  4. 2025Reasoning Capabilities of Large Language Models on Dynamic Tasks
  5. 2023StrategyLLM: Large Language Models as Strategy Generators, Executors, Optimizers, and Evaluators for Problem Solving
  6. 2025You Don't Need Prompt Engineering Anymore: The Prompting Inversion
  7. 2024Can Large Language Models Invent Algorithms to Improve Themselves?: Algorithm Discovery for Recursive Self-Improvement through Reinforcement Learning
  8. 2026Beyond the Answer: Decoding the Behavior of LLMs as Scientific Reasoners