mlsanityData to 7 Oct 2026

Evolution through Large Models

arXiv 2206.08896 ↗First posted 17 Jun 2022cs.NEcited by 131

Not on the map. Why?

Cited by 20 in LLM agents and tool use, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

This paper pursues the insight that large language models (LLMs) trained to generate code can vastly improve the effectiveness of mutation operators applied to programs in genetic programming (GP). Because such LLMs benefit from training data that includes sequential changes and modifications, they can approximate likely changes that humans would make. To highlight the breadth of implications of such evolution through large models (ELM), in the main experiment ELM combined with MAP-Elites generates hundreds of thousands of functional examples of Python programs that output working ambulating robots in the Sodarace domain, which the original LLM had never seen in pre-training. These examples then help to bootstrap training a new conditional language model that can output the right walker for a particular terrain. The ability to bootstrap new models that can output appropriate artifacts for a given context in a domain where zero training data was previously available carries implications for open-endedness, deep learning, and reinforcement learning. These implications are explored here in depth in the hope of inspiring new directions of research now opened up by ELM.

Key facts. Cited by 131 papers in the map (data through 7 Oct 2026). First posted on arXiv 17 Jun 2022.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 19; 2024: 31; 2025: 33; 2026: 46.

131 papers.

Sort:

By area:

  1. 2023Large Language Models as Optimizerscited by 830
  2. 2025AlphaEvolve: A coding agent for scientific and algorithmic discoverycited by 763
  3. 2023Eureka: Human-Level Reward Design via Coding Large Language Modelscited by 542
  4. 2023Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolutioncited by 521
  5. 2024ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolutioncited by 266
  6. 2024Evolution of Heuristics: Towards Efficient Automatic Algorithm Design Using Large Language Modelcited by 258
  7. 2023EvoPrompt: Connecting LLMs with Evolutionary Algorithms Yields Powerful Prompt Optimizerscited by 189
  8. 2023OctoPack: Instruction Tuning Code Large Language Modelscited by 178
  9. 2024Teaching Large Language Models to Reason with Reinforcement Learningcited by 158
  10. 2024AgentSquare: Automatic LLM Agent Search in Modular Design Spacecited by 141
  11. 2023EvoPrompting: Language Models for Code-Level Neural Architecture Searchcited by 129
  12. 2024Large Language Models to Enhance Bayesian Optimizationcited by 127
38 more
  1. 2024LLM-SR: Scientific Equation Discovery via Programming with Large Language Modelscited by 117
  2. 2024Evolutionary Computation in the Era of Large Language Model: Survey and Roadmapcited by 89
  3. 2023LLMatic: Neural Architecture Search via Large Language Models and Quality Diversity Optimizationcited by 86
  4. 2024Open-Endedness is Essential for Artificial Superhuman Intelligencecited by 79
  5. 2023MarioGPT: Open-Ended Text2Level Generation through Large Language Modelscited by 63
  6. 2024Efficient Evolutionary Search Over Chemical Space with Large Language Modelscited by 59
  7. 2023Algorithm Evolution Using Large Language Modelcited by 52
  8. 2025Towards Robust Agentic CUDA Kernel Benchmarking, Verification, and Optimizationcited by 52
  9. 2026AdaEvolve: Adaptive LLM Driven Zeroth-Order Optimizationcited by 46
  10. 2024LLaMoCo: Instruction Tuning of Large Language Models for Optimization Code Generationcited by 45
  11. 2024Evolving Code with A Large Language Modelcited by 42
  12. 2023Quality-Diversity through AI Feedbackcited by 40
  13. 2024Discovering Preference Optimization Algorithms with and for Large Language Modelscited by 38
  14. 2025LLM-FE: Automated Feature Engineering for Tabular Data with LLMs as Evolutionary Optimizerscited by 35
  15. 2025Self-Improving Language Models for Evolutionary Program Synthesis: A Case Study on ARC-AGIcited by 34
  16. 2024Surveying the Effects of Quality, Diversity, and Complexity in Synthetic Data From Large Language Modelscited by 31
  17. 2023Large Language Model for Multi-objective Evolutionary Optimizationcited by 29
  18. 2024LICO: Large Language Models for In-Context Molecular Optimizationcited by 26
  19. 2024GAVEL: Generating Games Via Evolution and Language Modelscited by 24
  20. 2024Toward Automated Algorithm Design: A Survey and Practical Guide to Meta-Black-Box-Optimizationcited by 23
  21. 2024FunBO: Discovering Acquisition Functions for Bayesian Optimization with FunSearchcited by 22
  22. 2024Prompt-A-Video: Prompt Your Video Diffusion Model via Preference-Aligned LLMcited by 22
  23. 2024Position: Leverage Foundational Models for Black-Box Optimizationcited by 21
  24. 2022General Intelligence Requires Rethinking Explorationcited by 20
  25. 2024Automating the Search for Artificial Life with Foundation Modelscited by 20
  26. 2026Towards Execution-Grounded Automated AI Researchcited by 19
  27. 2026AVO: Agentic Variation Operators for Autonomous Evolutionary Searchcited by 19
  28. 2023An evolutionary model of personality traits related to cooperative behavior using a large language modelcited by 18
  29. 2025Adaptive Kernel Design for Bayesian Optimization Is a Piece of CAKE with LLMscited by 15
  30. 2024Pretrained Optimization Model for Zero-Shot Black Box Optimizationcited by 13
  31. 2024Deep Insights into Automated Optimization with Large Language Models and Evolutionary Algorithmscited by 12
  32. 2025LLEMA: Evolutionary Search with LLMs for Multi-Objective Materials Discoverycited by 11
  33. 2026KernelFoundry: Hardware-aware evolutionary GPU kernel optimizationcited by 11
  34. 2025DISC: Dynamic Decomposition Improves LLM Inference Scalingcited by 9
  35. 2025EvoGit: Decentralized Code Evolution via Git-Based Multi-Agent Collaborationcited by 9
  36. 2024From Text to Life: On the Reciprocal Relationship between Artificial Life and Large Language Modelscited by 8
  37. 2024Generalists vs. Specialists: Evaluating LLMs on Highly-Constrained Biophysical Sequence Optimization Taskscited by 8
  38. 2024Large Language Models as In-context AI Generators for Quality-Diversitycited by 7

50 most cited of 131 All 131 (JSON)