mlsanityData to 7 Oct 2026

Illuminating search spaces by mapping elites

arXiv 1504.04909 ↗First posted 20 Apr 2015cs.AI cs.NE cs.ROcited by 406

Not on the map. Why?

Cited by 46 in LLM agents and tool use, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Many fields use search algorithms, which automatically explore a search space to find high-performing solutions: chemists search through the space of molecules to discover new drugs; engineers search for stronger, cheaper, safer designs, scientists search for models that best explain data, etc. The goal of search algorithms has traditionally been to return the single highest-performing solution in a search space. Here we describe a new, fundamentally different type of algorithm that is more useful because it provides a holistic view of how high-performing solutions are distributed throughout a search space. It creates a map of high-performing solutions at each point in a space defined by dimensions of variation that a user gets to choose. This Multi-dimensional Archive of Phenotypic Elites (MAP-Elites) algorithm illuminates search spaces, allowing researchers to understand how interesting attributes of solutions combine to affect performance, either positively or, equally of interest, negatively. For example, a drug company may wish to understand how performance changes as the size of molecules and their cost-to-produce vary. MAP-Elites produces a large diversity of high-performing, yet qualitatively different solutions, which can be more helpful than a single, high-performing solution. Interestingly, because MAP-Elites explores more of the search space, it also tends to find a better overall solution than state-of-the-art search algorithms. We demonstrate the benefits of this new algorithm in three different problem domains ranging from producing modular neural networks to designing simulated and real soft robots. Because MAP- Elites (1) illuminates the relationship between performance and dimensions of interest in solutions, (2) returns a set of high-performing, yet diverse solutions, and (3) improves finding a single, best solution, it will advance science and engineering.

Key facts. Cited by 406 papers in the map (data through 7 Oct 2026). First posted on arXiv 20 Apr 2015.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 33; 2022: 53; 2023: 60; 2024: 47; 2025: 59; 2026: 154.

406 papers.

Sort:

By area:

  1. 2025AlphaEvolve: A coding agent for scientific and algorithmic discoverycited by 763
  2. 2023Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolutioncited by 521
  3. 2024Automated Design of Agentic Systemscited by 360
  4. 2025Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agentscited by 294
  5. 2023EvoPrompt: Connecting LLMs with Evolutionary Algorithms Yields Powerful Prompt Optimizerscited by 189
  6. 2024Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Promptscited by 189
  7. 2026Towards End-to-End Automation of AI Researchcited by 150
  8. 2022Walk These Ways: Tuning Robot Control for Generalization with Multiplicity of Behaviorcited by 113
  9. 2025The Attacker Moves Second: Stronger Adaptive Attacks Bypass Defenses Against Llm Jailbreaks and Prompt Injectionscited by 108
  10. 2025Agentic Large Language Models, a surveycited by 105
  11. 2023Motif: Intrinsic Motivation from Artificial Intelligence Feedbackcited by 99
  12. 2024Evolutionary Computation in the Era of Large Language Model: Survey and Roadmapcited by 89
38 more
  1. 2023LLMatic: Neural Architecture Search via Large Language Models and Quality Diversity Optimizationcited by 86
  2. 2024Open-Endedness is Essential for Artificial Superhuman Intelligencecited by 79
  3. 2021Differentiable Quality Diversitycited by 71
  4. 2023OMNI: Open-endedness via Models of human Notions of Interestingnesscited by 66
  5. 2023MarioGPT: Open-Ended Text2Level Generation through Large Language Modelscited by 63
  6. 2022Winner Takes It All: Training Performant RL Populations for Combinatorial Optimizationcited by 57
  7. 2022Diversify and Disambiguate: Learning From Underspecified Datacited by 55
  8. 2025ThetaEvolve: Test-time Learning on Open Problemscited by 52
  9. 2021Revisiting Design Choices in Offline Model-Based Reinforcement Learningcited by 50
  10. 2025Barbarians at the Gate: How AI is Upending Systems Researchcited by 48
  11. 2022Deep Surrogate Assisted Generation of Environmentscited by 40
  12. 2023Quality-Diversity through AI Feedbackcited by 40
  13. 2021Modelling Behavioural Diversity for Learning in Open-Ended Gamescited by 39
  14. 2021On the Importance of Environments in Human-Robot Coordinationcited by 37
  15. 2022Approximating Gradients for Differentiable Quality Diversity in Reinforcement Learningcited by 37
  16. 2025CodeEvolve: an open source evolutionary coding agent for algorithmic discovery and optimizationcited by 37
  17. 2021Illuminating Diverse Neural Cellular Automata for Level Generationcited by 35
  18. 2022Discovering Policies with DOMiNO: Diversity Optimization Maintaining Near Optimalitycited by 35
  19. 2026AttriGuard: Defeating Indirect Prompt Injection in LLM Agents via Causal Attribution of Tool Invocationscited by 33
  20. 2026Group-Evolving Agents: Open-Ended Self-Improvement via Experience Sharingcited by 32
  21. 2024Surveying the Effects of Quality, Diversity, and Complexity in Synthetic Data From Large Language Modelscited by 31
  22. 2021Unsupervised Behaviour Discovery with Quality-Diversity Optimisationcited by 30
  23. 2021DeepHyperion: Exploring the Feature Space of Deep Learning-Based Systems through Illumination Searchcited by 29
  24. 2022Discovering Many Diverse Solutions with Bayesian Optimizationcited by 29
  25. 2023pyribs: A Bare-Bones Python Library for Quality Diversity Optimizationcited by 29
  26. 2021Generating and Blending Game Levels via Quality-Diversity in the Latent Space of a Variational Autoencodercited by 27
  27. 2026Neural Thickets: Diverse Task Experts Are Dense Around Pretrained Weightscited by 25
  28. 2021Diverse Auto-Curriculum is Critical for Successful Real-World Multiagent Learning Systemscited by 24
  29. 2022Covariance Matrix Adaptation MAP-Annealingcited by 24
  30. 2023Evolutionary Reinforcement Learning: A Surveycited by 24
  31. 2023Cousins Of The Vendi Score: A Family Of Similarity-Based Diversity Metrics For Science And Machine Learningcited by 24
  32. 2024GAVEL: Generating Games Via Evolution and Language Modelscited by 24
  33. 2022Neuroevolution is a Competitive Alternative to Reinforcement Learning for Skill Discoverycited by 23
  34. 2024Bridging Evolutionary Algorithms and Reinforcement Learning: A Comprehensive Survey on Hybrid Algorithmscited by 23
  35. 2025GPU Kernel Scientist: An LLM-Driven Framework for Iterative Kernel Optimizationcited by 22
  36. 2021Policy Manifold Search: Exploring the Manifold Hypothesis for Diversity-based Neuroevolutioncited by 20
  37. 2021Discovering Diverse Nearly Optimal Policies with Successor Featurescited by 20
  38. 2021Dynamics-Aware Quality-Diversity for Efficient Learning of Skill Repertoirescited by 20

50 most cited of 406 All 406 (JSON)