mlsanityData to 7 Oct 2026

Large Language Models as Optimizers

arXiv 2309.03409 ↗First posted 7 Sep 2023cs.LG cs.AI cs.CLcited by 830

Not on the map. Why?

Cited by 190 in LLM agents and tool use, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Optimization is ubiquitous. While derivative-based algorithms have been powerful tools for various problems, the absence of gradient imposes challenges on many real-world applications. In this work, we propose Optimization by PROmpting (OPRO), a simple and effective approach to leverage large language models (LLMs) as optimizers, where the optimization task is described in natural language. In each optimization step, the LLM generates new solutions from the prompt that contains previously generated solutions with their values, then the new solutions are evaluated and added to the prompt for the next optimization step. We first showcase OPRO on linear regression and traveling salesman problems, then move on to our main application in prompt optimization, where the goal is to find instructions that maximize the task accuracy. With a variety of LLMs, we demonstrate that the best prompts optimized by OPRO outperform human-designed prompts by up to 8% on GSM8K, and by up to 50% on Big-Bench Hard tasks. Code at https://github.com/google-deepmind/opro.

Key facts. Cited by 830 papers in the map (data through 7 Oct 2026). Builds on 50 of its 72 references that are in the map. First posted on arXiv 7 Sep 2023.

Builds on

50 of 72 references.

References · 50

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  3. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  4. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  5. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  6. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  7. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,878
  8. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,769
  9. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,317
  10. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 2,950
  11. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,081
  12. 2022Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language modelscited by 1,970
38 more
  1. 2022Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Themcited by 1,767
  2. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Modelscited by 1,397
  3. 2021Calibrate Before Use: Improving Few-Shot Performance of Language Modelscited by 1,371
  4. 2020Making Pre-trained Language Models Better Few-shot Learnerscited by 1,255
  5. 2023PaLM 2 Technical Reportcited by 1,154
  6. 2021Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivitycited by 1,122
  7. 2023WizardLM: Empowering large pre-trained language models to follow complex instructionscited by 1,116
  8. 2022Large Language Models Are Human-Level Prompt Engineerscited by 1,020
  9. 2023Teaching Large Language Models to Self-Debugcited by 963
  10. 2021GPT Understands, Toocited by 715
  11. 2018Attention, Learn to Solve Routing Problems!cited by 646
  12. 2017Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problemscited by 642
  13. 2023Automatic Prompt Optimization with "Gradient Descent" and Beam Searchcited by 628
  14. 2021Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigmcited by 599
  15. 2023Larger language models do in-context learning differentlycited by 386
  16. 2021Learning How to Ask: Querying LMs with Mixtures of Soft Promptscited by 376
  17. 2023Language Models can Solve Computer Taskscited by 371
  18. 2022RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learningcited by 361
  19. 2016Solving General Arithmetic Word Problemscited by 353
  20. 2023Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discoverycited by 329
  21. 2018Reinforcement Learning for Solving the Vehicle Routing Problemcited by 327
  22. 2023Large Language Models as Tool Makerscited by 293
  23. 2023Large Language Models as General Pattern Machinescited by 196
  24. 2018Learning to Perform Local Rewriting for Combinatorial Optimizationcited by 183
  25. 2023The Capacity for Moral Self-Correction in Large Language Modelscited by 171
  26. 2022Evolution through Large Modelscited by 131
  27. 2023EvoPrompting: Language Models for Code-Level Neural Architecture Searchcited by 129
  28. 2022Text and Patterns: For Effective Chain of Thought, It Takes Two to Tangocited by 128
  29. 2022GrIPS: Gradient-free, Edit-based Instruction Search for Prompting Large Language Modelscited by 127
  30. 2023Language Model Crossover: Variation through Few-Shot Promptingcited by 119
  31. 2022Towards Learning Universal Hyperparameter Optimizers with Transformerscited by 81
  32. 2023Improving Code Generation by Training with Natural Language Feedbackcited by 75
  33. 2023InstructZero: Efficient Instruction Optimization for Black-Box Large Language Modelscited by 68
  34. 2023DERA: Enhancing Large Language Model Completions with Dialog-Enabled Resolving Agentscited by 52
  35. 2022GPS: Genetic Prompt Search for Efficient Few-shot Learningcited by 37
  36. 2023When do you need Chain-of-Thought Prompting for ChatGPT?cited by 34
  37. 2023Let's Do a Thought Experiment: Using Counterfactuals to Improve Moral Reasoningcited by 20
  38. 2023System-Level Natural Language Feedbackcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 55; 2024: 212; 2025: 203; 2026: 360.

830 papers.

Sort:

By area:

  1. 2023Large Language Models Cannot Self-Correct Reasoning Yetcited by 965
  2. 2023DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelinescited by 803
  3. 2023Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolutioncited by 521
  4. 2024A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applicationscited by 428
  5. 2024AFlow: Automating Agentic Workflow Generationcited by 395
  6. 2024Automated Design of Agentic Systemscited by 360
  7. 2023Can Generalist Foundation Models Outcompete Special-Purpose Tuning? Case Study in Medicinecited by 319
  8. 2024Massive Activations in Large Language Modelscited by 277
  9. 2024ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolutioncited by 266
  10. 2024Evolution of Heuristics: Towards Efficient Automatic Algorithm Design Using Large Language Modelcited by 258
  11. 2024To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoningcited by 257
  12. 2024TextGrad: Automatic "Differentiation" via Textcited by 250
38 more
  1. 2026Meta-Harness: End-to-End Optimization of Model Harnessescited by 248
  2. 2024Scaling Large Language Model-based Multi-Agent Collaborationcited by 235
  3. 2024When Can LLMs Actually Correct Their Own Mistakes? A Critical Survey of Self-Correction of LLMscited by 230
  4. 2023PromptAgent: Strategic Planning with Language Models Enables Expert-level Prompt Optimizationcited by 226
  5. 2023Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theorycited by 218
  6. 2024Chain-of-Thought Reasoning Without Promptingcited by 208
  7. 2023Universal Self-Consistency for Large Language Model Generationcited by 198
  8. 2024PIVOT: Iterative Visual Prompting Elicits Actionable Knowledge for VLMscited by 187
  9. 2023Efficient Large Language Models: A Surveycited by 183
  10. 2023Talk like a Graph: Encoding Graphs for Large Language Modelscited by 175
  11. 2024AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMscited by 160
  12. 2023Take a Step Back: Evoking Reasoning via Abstraction in Large Language Modelscited by 157
  13. 2025A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligencecited by 155
  14. 2024Improving Instruction-Following in Language Models through Activation Steeringcited by 149
  15. 2023PaperQA: Retrieval-Augmented Generative Agent for Scientific Researchcited by 143
  16. 2024AgentSquare: Automatic LLM Agent Search in Modular Design Spacecited by 141
  17. 2024A Human-Inspired Reading Agent with Gist Memory of Very Long Contextscited by 140
  18. 2023Self-Taught Optimizer (STOP): Recursively Self-Improving Code Generationcited by 128
  19. 2024Large Language Models to Enhance Bayesian Optimizationcited by 127
  20. 2026SkillOpt: Executive Strategy for Self-Evolving Agent Skillscited by 122
  21. 2023Chain of Code: Reasoning with a Language Model-Augmented Code Emulatorcited by 120
  22. 2024Empowering Biomedical Discovery with AI Agentscited by 117
  23. 2024LLM-SR: Scientific Equation Discovery via Programming with Large Language Modelscited by 117
  24. 2025X-Teaming: Multi-Turn Jailbreaks and Defenses with Adaptive Multi-Agentscited by 112
  25. 2024On Prompt-Driven Safeguarding for Large Language Modelscited by 109
  26. 2024Self-Discover: Large Language Models Self-Compose Reasoning Structurescited by 108
  27. 2025Multi-Agent Design: Optimizing Agents with Better Prompts and Topologiescited by 106
  28. 2024Symbolic Learning Enables Self-Evolving Agentscited by 104
  29. 2024LLMOPT: Learning to Define and Solve General Optimization Problems from Scratchcited by 102
  30. 2025Monte Carlo Tree Search for Comprehensive Exploration in LLM-Based Automatic Heuristic Designcited by 100
  31. 2024Evolutionary Computation in the Era of Large Language Model: Survey and Roadmapcited by 89
  32. 2024Improving Text-to-Image Consistency via Automatic Prompt Optimizationcited by 88
  33. 2024Large Language Model (LLM) for Telecommunications: A Comprehensive Survey on Principles, Key Techniques, and Opportunitiescited by 83
  34. 2024LLM and Simulation as Bilevel Optimizers: A New Paradigm to Advance Physical Scientific Discoverycited by 82
  35. 2024Metacognitive Capabilities of LLMs: An Exploration in Mathematical Problem Solvingcited by 82
  36. 2024Language Agents as Optimizable Graphscited by 81
  37. 2024Embodied LLM Agents Learn to Cooperate in Organized Teamscited by 81
  38. 2024Open-Endedness is Essential for Artificial Superhuman Intelligencecited by 79

50 most cited of 830 All 830 (JSON)