# DesignX: Human-Competitive Algorithm Designer for Black-Box Optimization

arXiv: https://arxiv.org/abs/2505.17866 · HTML: https://mlsanity.com/paper/2505.17866/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 116 references that are in the map.
- First posted on arXiv 23 May 2025.

## Builds on (most cited first, 30 of 35)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [Eureka: Human-Level Reward Design via Coding Large Language Models](https://mlsanity.com/paper/2310.12931/) (2023)
- [AutoML: A Survey of the State-of-the-Art](https://mlsanity.com/paper/1908.00709/) (2019)
- [Evolution of Heuristics: Towards Efficient Automatic Algorithm Design Using Large Language Model](https://mlsanity.com/paper/2401.02051/) (2024)
- [Learning to Optimize: A Primer and A Benchmark](https://mlsanity.com/paper/2103.12828/) (2021)
- [COCO: A Platform for Comparing Continuous Optimizers in a Black-Box Setting](https://mlsanity.com/paper/1603.08785/) (2016)
- [LLMOPT: Learning to Define and Solve General Optimization Problems from Scratch](https://mlsanity.com/paper/2410.13213/) (2024)
- [HPO-B: A Large-Scale Reproducible Benchmark for Black-Box HPO based on OpenML](https://mlsanity.com/paper/2106.06257/) (2021)
- [Machine Learning for Electronic Design Automation: A Survey](https://mlsanity.com/paper/2102.03357/) (2021)
- [LLaMoCo: Instruction Tuning of Large Language Models for Optimization Code Generation](https://mlsanity.com/paper/2403.01131/) (2024)
- [Deep Reinforcement Learning Based Parameter Control in Differential Evolution](https://mlsanity.com/paper/1905.08006/) (2019)
- [Multi-agent Dynamic Algorithm Configuration](https://mlsanity.com/paper/2210.06835/) (2022)
- [Exploratory Landscape Analysis is Strongly Sensitive to the Sampling Strategy](https://mlsanity.com/paper/2006.11135/) (2020)
- [Learning adaptive differential evolution algorithm from optimization experiences by policy gradient](https://mlsanity.com/paper/2102.03572/) (2021)
- [Deep Reinforcement Learning for Dynamic Algorithm Selection: A Proof-of-Principle Study on Differential Evolution](https://mlsanity.com/paper/2403.02131/) (2024)
- [Toward Automated Algorithm Design: A Survey and Practical Guide to Meta-Black-Box-Optimization](https://mlsanity.com/paper/2411.00625/) (2024)
- [Symbol: Generating Flexible Black-Box Optimizers through Symbolic Equation Learning](https://mlsanity.com/paper/2402.02355/) (2024)
- [Auto-configuring Exploration-Exploitation Tradeoff in Evolutionary Computation via Deep Reinforcement Learning](https://mlsanity.com/paper/2404.08239/) (2024)
- [B2Opt: Learning to Optimize Black-box Optimization with Little Budget](https://mlsanity.com/paper/2304.11787/) (2023)
- [ConfigX: Modular Configuration for Evolutionary Algorithms via Multitask Reinforcement Learning](https://mlsanity.com/paper/2412.07507/) (2024)
- [Reinforcement Learning-based Self-adaptive Differential Evolution through Automated Landscape Feature Learning](https://mlsanity.com/paper/2503.18061/) (2025)
- [Evolving the Structure of Evolution Strategies](https://mlsanity.com/paper/1610.05231/) (2016)
- [Neural Exploratory Landscape Analysis for Meta-Black-Box-Optimization](https://mlsanity.com/paper/2408.10672/) (2024)
- [MMES: Mixture Model based Evolution Strategy for Large-Scale Optimization](https://mlsanity.com/paper/2203.12675/) (2022)
- [Meta-Black-Box-Optimization through Offline Q-function Learning](https://mlsanity.com/paper/2505.02010/) (2025)

## Built on by (most cited first, 5 of 5)

- [AutoEP: LLMs-Driven Automation of Hyperparameter Evolution for Metaheuristic Algorithms](https://mlsanity.com/paper/2509.23189/) (2025)
- [ScienceFlow: A long-horizon agent for ML research, scientific discovery and beyond](https://mlsanity.com/paper/2608.14354/) (2026)
- [Learning Where, What and How to Transfer: A Multi-Role Reinforcement Learning Approach for Evolutionary Multitasking](https://mlsanity.com/paper/2511.15199/) (2025)
- [Meta-Black-Box Optimization with Ensemble Surrogate Modeling for Robustness-Accuracy Trade-off within SAEA](https://mlsanity.com/paper/2606.00862/) (2026)
- [READY: Reward Discovery for Meta-Black-Box Optimization](https://mlsanity.com/paper/2601.21847/) (2026)

## Abstract (arXiv)

Designing effective black-box optimizers is hampered by limited problem-specific knowledge and manual control that spans months for almost every detail. In this paper, we present textitDesignX, the first automated algorithm design framework that generates an effective optimizer specific to a given black-box optimization problem within seconds. Rooted in the first principles, we identify two key sub-tasks: 1) algorithm structure generation and 2) hyperparameter control. To enable systematic construction, a comprehensive modular algorithmic space is first built, embracing hundreds of algorithm components collected from decades of research. We then introduce a dual-agent reinforcement learning system that collaborates on structural and parametric design through a novel cooperative training objective, enabling large-scale meta-training across 10k diverse instances. Remarkably, through days of autonomous learning, the DesignX-generated optimizers continuously surpass human-crafted optimizers by orders of magnitude, either on synthetic testbed or on realistic optimization scenarios such as Protein-docking, AutoML and UAV path planning. Further in-depth analysis reveals DesignX's capability to discover non-trivial algorithm patterns beyond expert intuition, which, conversely, provides valuable design insights for the optimization community. We provide DesignX's Python project at~ https://github.com/MetaEvo/DesignX.