The CMA Evolution Strategy: A Tutorial
Not on the map. Why?
Abstract (arXiv)
This tutorial introduces the CMA Evolution Strategy (ES), where CMA stands for Covariance Matrix Adaptation. The CMA-ES is a stochastic, or randomized, method for real-parameter (continuous domain) optimization of non-linear, non-convex functions. We try to motivate and derive the algorithm from intuitive concepts and from requirements of non-linear, non-convex search in continuous domain.
Key facts. Cited by 364 papers in the map (data through 7 Oct 2026). First posted on arXiv 4 Apr 2016.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 42; 2022: 46; 2023: 48; 2024: 59; 2025: 85; 2026: 84.
364 papers.
Sort:
By area:
- 2022Black-Box Tuning for Language-Model-as-a-Servicecited by 254
- 2021Neural Symbolic Regression that Scalescited by 185
- 2021Maximum Entropy RL (Provably) Solves Some Robust RL Problemscited by 169
- 2023Tree-Structured Parzen Estimator: Understanding Its Algorithm Components and Their Roles for Better Empirical Performancecited by 143
- 2025Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systemscited by 125
- 2021Paint by Wordcited by 107
- 2021AutoFlow: Learning a Better Training Set for Optical Flowcited by 102
- 2021Constrained Graphic Layout Generation via Latent Optimizationcited by 83
- 2023Diffusion Models for Black-Box Optimizationcited by 75
- 2024Test-Time Model Adaptation with Only Forward Passescited by 74
- 2022Auditing Privacy Defenses in Federated Learning via Generative Gradient Leakagecited by 72
- 2021Differentiable Quality Diversitycited by 71
38 more
- 2023InstructZero: Efficient Instruction Optimization for Black-Box Large Language Modelscited by 68
- 2022A Survey on Model-based Reinforcement Learningcited by 65
- 2023MarioGPT: Open-Ended Text2Level Generation through Large Language Modelscited by 63
- 2021Unbiased Gradient Estimation in Unrolled Computation Graphs with Persistent Evolution Strategiescited by 52
- 2021Fast and Efficient Locomotion via Learned Gait Transitionscited by 50
- 2024COMBO: Compositional World Models for Embodied Multi-Agent Cooperationcited by 47
- 2024Training of Physical Neural Networkscited by 47
- 2022Approximate Differentiable Rendering with Algebraic Surfacescited by 44
- 2021LassoBench: A High-Dimensional Hyperparameter Optimization Benchmark Suite for Lassocited by 41
- 2022Differentiable Simulation of Soft Multi-body Systemscited by 39
- 2021Efficient Differentiable Simulation of Articulated Bodiescited by 38
- 2021On the Importance of Environments in Human-Robot Coordinationcited by 37
- 2022Approximating Gradients for Differentiable Quality Diversity in Reinforcement Learningcited by 37
- 2022Monte Carlo Tree Search based Variable Selection for High Dimensional Bayesian Optimizationcited by 37
- 2025What Drives Success in Physical Planning with Joint-Embedding Predictive World Models?cited by 37
- 2021Illuminating Diverse Neural Cellular Automata for Level Generationcited by 35
- 2023World Models and Predictive Coding for Cognitive and Developmental Robotics: Frontiers and Challengescited by 35
- 2021Bayesian Optimization of Function Networkscited by 33
- 2021Action-Sufficient State Representation Learning for Control with Structural Constraintscited by 31
- 2022Neural MoCon: Neural Motion Control for Physically Plausible Human Motion Capturecited by 31
- 2024Model-Based Diffusion for Trajectory Optimizationcited by 30
- 2022Discovering Many Diverse Solutions with Bayesian Optimizationcited by 29
- 2023pyribs: A Bare-Bones Python Library for Quality Diversity Optimizationcited by 29
- 2024LLMPhy: Parameter-Identifiable Physical Reasoning Combining Large Language Models and Physics Enginescited by 29
- 2023Gradient-Free Textual Inversioncited by 28
- 2022Safe Control Under Input Limits with Neural Control Barrier Functionscited by 27
- 2021Black-box Adversarial Attacks on Commercial Speech Platforms with Minimal Informationcited by 25
- 2023FedBPT: Efficient Federated Black-box Prompt Tuning for Large Language Modelscited by 25
- 2024Is Your LiDAR Placement Optimized for 3D Scene Understanding?cited by 25
- 2022Covariance Matrix Adaptation MAP-Annealingcited by 24
- 2022The Free Energy Principle for Perception and Action: A Deep Learning Perspectivecited by 24
- 2022CPG-RL: Learning Central Pattern Generators for Quadruped Locomotioncited by 24
- 2023Grounding Foundation Models through Federated Transfer Learning: A General Frameworkcited by 24
- 2025Eva-VLA: Evaluating Vision-Language-Action Models' Robustness Under Real-World Physical Variationscited by 24
- 2021Bayesian Optimization over Hybrid Spacescited by 23
- 2021Deep Reinforcement Learning Versus Evolution Strategies: A Comparative Surveycited by 23
- 2024Toward Automated Algorithm Design: A Survey and Practical Guide to Meta-Black-Box-Optimizationcited by 23
- 2026DeltaEvolve: Accelerating Scientific Discovery through Momentum-Driven Evolutioncited by 23
50 most cited of 364 All 364 (JSON)
- 2026LeWAM: A JEPA World Action Model with Diffusion-Steering-Based MPC8 Oct 2026
- 2026A Closer Look at Agentic BBO: Benchmarking LLM Agents for Black-Box Optimization8 Oct 2026
- 2026Continual Reinforcement Learning with Neuroevolution1 Oct 2026
- 2026MatLoom: Layered Text-to-Material Generation in a Compact Program Space30 Sep 2026
- 2026Online Evolution Strategy for Flow-Matching VLA Policies via Self-Supervised Trajectory Distribution Optimization30 Sep 2026
- 2026Parameter-Free Zeroth-Order Optimization with Ellipsoidal Sampling29 Sep 2026
- 2026Behavioral Foundation Models for Quality Diversity28 Sep 2026
- 2026Evolving Dexterous Robots from Scratch27 Sep 2026
- 2026EmbodiedSWE: Coding Agents for Long Horizon Dexterous Robotics23 Sep 2026
- 2026Diverse and Adaptable Arm Coordination for Octopus-Crawling via Diffusion-Based Uncertainty-Aware Optimization17 Sep 2026
- 2026EGGROLL, Unrolled: Understanding and Improving Low-Rank Evolution Strategies at Scale10 Sep 2026
- 2026Rethinking Learnability in Offline Data-driven Optimization1 Sep 2026
38 more
- 2026Spec2Twin-Chain: Orchestrating Bi-Level Optimization with LLMs for Blockchain Digital Twin Construction30 Aug 2026
- 2026Diffusion-Based Inverse Design of Dielectric Resonator Metasurfaces for Shaping Smart Electromagnetic Environments30 Aug 2026
- 2026Mental Model Management: An Operator-Based Framework for LLM Memory16 Aug 2026
- 2026TANGCO: Learning Topology-Aware Capacity Allocation for Overload-driven Cascading Failures13 Aug 2026
- 2026Curvature-Aware Zeroth-Order Optimization for Memory-Efficient Test-Time Adaptation12 Aug 2026
- 2026Basin: Efficient and Extensible Numerical Optimization in Rust11 Aug 2026
- 2026Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models10 Aug 2026
- 2026Skaling: Chinchilla's Exponents Meet Kaplan's Coupling7 Aug 2026
- 2026Flow-Corrected Shape Optimization: Taming Manifold Drift in High-Dimensional 3D Models7 Aug 2026
- 2026Iterative Hybrid Discrete-Continuous Viewpoint Planning for UAV Photogrammetry6 Aug 2026
- 2026Search-Aided Joint Agent-Environment Reinforcement Learning for Robust Lifelong Multi-Agent Path Finding with Rotations6 Aug 2026
- 2026RAG-Stack: Co-Optimizing RAG Serving Performance and Quality4 Aug 2026
- 2026Hard Constraints, Smooth Gradients: Learning Feasible Inventory Policies via Differentiable Projection3 Aug 2026
- 2026Accelerating Evolutionary Strategy via Rao-Blackwellizing Realization of Uncertain Input3 Aug 2026
- 2026Adaptive Reconstruction of Bosonic Quantum States3 Aug 2026
- 2026Agentic Bayesian Optimization through Surrogate-Augmented Autoresearch31 Jul 2026
- 2026Optimizing Denoising Trajectories in dLLMs: A Lightweight Evolutionary Heuristic Approach15 Jul 2026
- 2026Neural Operator-enabled Topology-informed Evolutionary Strategy for PDE-Constrained Optimization8 Jul 2026
- 2026D2PO: Optimizing Diffusion Samplers via Dynamic Preference7 Jul 2026
- 2026Generative Refinement for Low-Budget Black-Box Optimization1 Jul 2026
- 2026Simplifying Flow Matching Transformations with Low-Rank Mixture Models29 Jun 2026
- 2026Bridging Spherical Black-Box Optimizers24 Jun 2026
- 2026Physics-Informed Eikonal Caging for Whole-Arm Manipulation Planning20 Jun 2026
- 2026Evolutionary Discovery of Developmental Reward Schedules in Deep Reinforcement Learning18 Jun 2026
- 2026Model Merging to Evolution: Parameter Space Exploration for Expert Models17 Jun 2026
- 2026BadWorld: Adversarial Attacks on World Models15 Jun 2026
- 2026Scratched Lenses, Shifted Depth: Passive Camera-Side Optical Attacks12 Jun 2026
- 2026Operator Calculus for Population-Based Optimization: Modular Convergence and Finite-Population Guarantees12 Jun 2026
- 2026Aerial Wildfire Suppression Planning with a Hybrid CNN-Cellular Automata Fire Model11 Jun 2026
- 2026Learning What to Remember: A Cognitively Grounded Multi-Factor Value Model for Agentic Memory11 Jun 2026
- 2026Towards Automated Discovery: A Review of Generative Models, Multimodal Learning and Closed-Loop Workflows in Inverse Materials Design1 Jun 2026
- 2026Consolidating Rewarded Perturbations for LLM Post-Training29 May 2026
- 2026AutoSG: LLM-Driven Solver Generation Solely from Task Prompts for Expensive Optimization25 May 2026
- 2026Prior Knowledge or Search? A Study of LLM Agents in Hardware-Aware Code Optimization19 May 2026
- 2026Latent Heuristic Search: Continuous Optimization for Automated Algorithm Design16 May 2026
- 2026EVA-0: Test-Time Model Evolution with Only Two Forward Passes per Sample15 May 2026
- 2026Gradient-Free Training of Spiking Neural Networks via Low-Rank Evolution Strategies14 May 2026
- 2026Parameter-Efficient Neuroevolution for Diverse LLM Generation: Quality-Diversity Optimization via Prompt Embedding Evolution10 May 2026
50 newest of 364 All 364 (JSON)
- 2023Diffusion Models for Black-Box Optimizationcited by 75
- 2024Model-Based Diffusion for Trajectory Optimizationcited by 30
- 2024Diffusion Models are Evolutionary Algorithmscited by 15
- 2025FlowMP: Learning Motion Fields for Robot Planning with Conditional Flow Matchingcited by 15
- 2025Diffusion-Based Electromagnetic Inverse Design of Scattering Structured Mediacited by 1
- 2025RSTR: Reducing SpatioTemporal Redundancy in Diffusion Transformerscited by 1
- 2025Sample-Efficient Optimisation over the Outputs of Generative Modelscited by 0
- 2026Simplifying Flow Matching Transformations with Low-Rank Mixture Modelscited by 0
- 2026D2PO: Optimizing Diffusion Samplers via Dynamic Preferencecited by 0
- 2026Flow-Corrected Shape Optimization: Taming Manifold Drift in High-Dimensional 3D Modelscited by 0
- 2026Flow-Corrected Shape Optimization: Taming Manifold Drift in High-Dimensional 3D Models7 Aug 2026
- 2026D2PO: Optimizing Diffusion Samplers via Dynamic Preference7 Jul 2026
- 2026Simplifying Flow Matching Transformations with Low-Rank Mixture Models29 Jun 2026
- 2025RSTR: Reducing SpatioTemporal Redundancy in Diffusion Transformers16 Dec 2025
- 2025Diffusion-Based Electromagnetic Inverse Design of Scattering Structured Media7 Nov 2025
- 2025Sample-Efficient Optimisation over the Outputs of Generative Models28 Sep 2025
- 2025FlowMP: Learning Motion Fields for Robot Planning with Conditional Flow Matching8 Mar 2025
- 2024Diffusion Models are Evolutionary Algorithms3 Oct 2024
- 2024Model-Based Diffusion for Trajectory Optimization28 May 2024
- 2023Diffusion Models for Black-Box Optimization12 Jun 2023
- 2022A Survey on Model-based Reinforcement Learningcited by 65
- 2024COMBO: Compositional World Models for Embodied Multi-Agent Cooperationcited by 47
- 2025What Drives Success in Physical Planning with Joint-Embedding Predictive World Models?cited by 37
- 2023World Models and Predictive Coding for Cognitive and Developmental Robotics: Frontiers and Challengescited by 35
- 2026Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world modelscited by 6
- 2026BadWorld: Adversarial Attacks on World Modelscited by 3
- 2022RLFlow: Optimising Neural Network Subgraph Transformation with World Modelscited by 0
- 2022Sample Efficient Robot Learning with Structured World Modelscited by 0
- 2026Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models10 Aug 2026
- 2026BadWorld: Adversarial Attacks on World Models15 Jun 2026
- 2025What Drives Success in Physical Planning with Joint-Embedding Predictive World Models?30 Dec 2025
- 2024COMBO: Compositional World Models for Embodied Multi-Agent Cooperation16 Apr 2024
- 2023World Models and Predictive Coding for Cognitive and Developmental Robotics: Frontiers and Challenges14 Jan 2023
- 2022Sample Efficient Robot Learning with Structured World Models21 Oct 2022
- 2022A Survey on Model-based Reinforcement Learning19 Jun 2022
- 2022RLFlow: Optimising Neural Network Subgraph Transformation with World Models3 May 2022
- 2025Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systemscited by 125
- 2026Can LLMs Beat Classical Hyperparameter Optimization Algorithms? A Study on autoresearchcited by 12
- 2026Agentic Bayesian Optimization through Surrogate-Augmented Autoresearchcited by 5
- 2026EmbodiedSWE: Coding Agents for Long Horizon Dexterous Roboticscited by 2
- 2026Prior Knowledge or Search? A Study of LLM Agents in Hardware-Aware Code Optimizationcited by 1
- 2025A Multi-Agent Framework for Stateful Inference-Time Searchcited by 0
- 2026Learning What to Remember: A Cognitively Grounded Multi-Factor Value Model for Agentic Memorycited by 0
- 2026EmbodiedSWE: Coding Agents for Long Horizon Dexterous Robotics23 Sep 2026
- 2026Agentic Bayesian Optimization through Surrogate-Augmented Autoresearch31 Jul 2026
- 2026Learning What to Remember: A Cognitively Grounded Multi-Factor Value Model for Agentic Memory11 Jun 2026
- 2026Prior Knowledge or Search? A Study of LLM Agents in Hardware-Aware Code Optimization19 May 2026
- 2026Can LLMs Beat Classical Hyperparameter Optimization Algorithms? A Study on autoresearch25 Mar 2026
- 2025A Multi-Agent Framework for Stateful Inference-Time Search8 Oct 2025
- 2025Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems31 Mar 2025
- 2025Multi-objective Large Language Model Alignment with Hierarchical Expertscited by 10
- 2025Cultural Alignment in Large Language Models Using Soft Prompt Tuningcited by 4
- 2024Improving User Experience in Preference-Based Optimization of Reward Functions for Assistive Robotscited by 1
- 2025Explicit and Non-asymptotic Query Complexities of Rank-Based Zeroth-order Algorithm on Stochastic Smooth Functionscited by 0
- 2026EvoPref: Multi-Objective Evolutionary Optimization Discovers Diverse LLM Alignments Beyond Gradient Descentcited by 0
- 2026EvoPref: Multi-Objective Evolutionary Optimization Discovers Diverse LLM Alignments Beyond Gradient Descent10 May 2026
- 2025Explicit and Non-asymptotic Query Complexities of Rank-Based Zeroth-order Algorithm on Stochastic Smooth Functions22 Dec 2025
- 2025Multi-objective Large Language Model Alignment with Hierarchical Experts27 May 2025
- 2025Cultural Alignment in Large Language Models Using Soft Prompt Tuning20 Mar 2025
- 2024Improving User Experience in Preference-Based Optimization of Reward Functions for Assistive Robots17 Nov 2024
- 2025When Lighting Deceives: Exposing Vision-Language Models' Illumination Vulnerability Through Illumination Transformation Attackcited by 10
- 2024AdvDreamer Unveils: Are Vision-Language Models Truly Ready for Real-World 3D Variations?cited by 5
- 2025ZIP: An Efficient Zeroth-order Prompt Tuning for Black-box Vision-Language Modelscited by 4
- 2026Skeletonization-Based Adversarial Perturbations on Large Vision Language Model's Mathematical Text Recognitioncited by 0
- 2026Skeletonization-Based Adversarial Perturbations on Large Vision Language Model's Mathematical Text Recognition8 Jan 2026
- 2025ZIP: An Efficient Zeroth-order Prompt Tuning for Black-box Vision-Language Models9 Apr 2025
- 2025When Lighting Deceives: Exposing Vision-Language Models' Illumination Vulnerability Through Illumination Transformation Attack10 Mar 2025
- 2024AdvDreamer Unveils: Are Vision-Language Models Truly Ready for Real-World 3D Variations?4 Dec 2024
- 2024LLMPhy: Parameter-Identifiable Physical Reasoning Combining Large Language Models and Physics Enginescited by 29
- 2025Satori-SWE: Evolutionary Test-Time Scaling for Sample-Efficient Software Engineeringcited by 16
- 2025Reasoning BO: Enhancing Bayesian Optimization with Long-Context Reasoning Power of LLMscited by 8
- 2025Satori-SWE: Evolutionary Test-Time Scaling for Sample-Efficient Software Engineering29 May 2025
- 2025Reasoning BO: Enhancing Bayesian Optimization with Long-Context Reasoning Power of LLMs19 May 2025
- 2024LLMPhy: Parameter-Identifiable Physical Reasoning Combining Large Language Models and Physics Engines12 Nov 2024
- 2024Diversifying Policy Behaviors with Extrinsic Behavioral Curiositycited by 4
- 2024UnifiedRL: A Reinforcement Learning Algorithm Tailored for Multi-Task Fusion in Large-Scale Recommender Systemscited by 2
- 2024A context-adaptive policy framework for robust and reactive robotic manipulation via uncertainty-aware imitation learningcited by 0
- 2024A context-adaptive policy framework for robust and reactive robotic manipulation via uncertainty-aware imitation learning31 Oct 2024
- 2024Diversifying Policy Behaviors with Extrinsic Behavioral Curiosity8 Oct 2024
- 2024UnifiedRL: A Reinforcement Learning Algorithm Tailored for Multi-Task Fusion in Large-Scale Recommender Systems19 Apr 2024
- 2022Black-Box Tuning for Language-Model-as-a-Servicecited by 254
- 2021Neural Symbolic Regression that Scalescited by 185
- 2021Maximum Entropy RL (Provably) Solves Some Robust RL Problemscited by 169
- 2023Tree-Structured Parzen Estimator: Understanding Its Algorithm Components and Their Roles for Better Empirical Performancecited by 143
- 2021Paint by Wordcited by 107
- 2021AutoFlow: Learning a Better Training Set for Optical Flowcited by 102
- 2021Constrained Graphic Layout Generation via Latent Optimizationcited by 83
- 2024Test-Time Model Adaptation with Only Forward Passescited by 74
- 2022Auditing Privacy Defenses in Federated Learning via Generative Gradient Leakagecited by 72
- 2021Differentiable Quality Diversitycited by 71
- 2023InstructZero: Efficient Instruction Optimization for Black-Box Large Language Modelscited by 68
- 2023MarioGPT: Open-Ended Text2Level Generation through Large Language Modelscited by 63
12 most cited of 318 All 318 (JSON)
- 2026LeWAM: A JEPA World Action Model with Diffusion-Steering-Based MPC8 Oct 2026
- 2026A Closer Look at Agentic BBO: Benchmarking LLM Agents for Black-Box Optimization8 Oct 2026
- 2026Continual Reinforcement Learning with Neuroevolution1 Oct 2026
- 2026MatLoom: Layered Text-to-Material Generation in a Compact Program Space30 Sep 2026
- 2026Parameter-Free Zeroth-Order Optimization with Ellipsoidal Sampling29 Sep 2026
- 2026Behavioral Foundation Models for Quality Diversity28 Sep 2026
- 2026Evolving Dexterous Robots from Scratch27 Sep 2026
- 2026Diverse and Adaptable Arm Coordination for Octopus-Crawling via Diffusion-Based Uncertainty-Aware Optimization17 Sep 2026
- 2026EGGROLL, Unrolled: Understanding and Improving Low-Rank Evolution Strategies at Scale10 Sep 2026
- 2026Rethinking Learnability in Offline Data-driven Optimization1 Sep 2026
- 2026Spec2Twin-Chain: Orchestrating Bi-Level Optimization with LLMs for Blockchain Digital Twin Construction30 Aug 2026
- 2026Diffusion-Based Inverse Design of Dielectric Resonator Metasurfaces for Shaping Smart Electromagnetic Environments30 Aug 2026
12 newest of 318 All 318 (JSON)