# Instance Generation for Meta-Black-Box Optimization through Latent Space Reverse Engineering

arXiv: https://arxiv.org/abs/2509.15810 · HTML: https://mlsanity.com/paper/2509.15810/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 66 references that are in the map.
- First posted on arXiv 19 Sep 2025.

## Builds on (most cited first, 20 of 20)

- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Learning to Generalize: Meta-Learning for Domain Generalization](https://mlsanity.com/paper/1710.03463/) (2017)
- [LLaMEA: A Large Language Model Evolutionary Algorithm for Automatically Generating Metaheuristics](https://mlsanity.com/paper/2405.20132/) (2024)
- [HPO-B: A Large-Scale Reproducible Benchmark for Black-Box HPO based on OpenML](https://mlsanity.com/paper/2106.06257/) (2021)
- [Meta-Learning Requires Meta-Augmentation](https://mlsanity.com/paper/2007.05549/) (2020)
- [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)
- [MetaBox: A Benchmark Platform for Meta-Black-Box Optimization with Reinforcement Learning](https://mlsanity.com/paper/2310.08252/) (2023)
- [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)
- [Symbol: Generating Flexible Black-Box Optimizers through Symbolic Equation Learning](https://mlsanity.com/paper/2402.02355/) (2024)
- [ConfigX: Modular Configuration for Evolutionary Algorithms via Multitask Reinforcement Learning](https://mlsanity.com/paper/2412.07507/) (2024)
- [Benchmarking Discrete Optimization Heuristics with IOHprofiler](https://mlsanity.com/paper/1912.09237/) (2019)
- [DoE2Vec: Deep-learning Based Features for Exploratory Landscape Analysis](https://mlsanity.com/paper/2304.01219/) (2023)
- [Reinforcement Learning-based Self-adaptive Differential Evolution through Automated Landscape Feature Learning](https://mlsanity.com/paper/2503.18061/) (2025)
- [MA-BBOB: A Problem Generator for Black-Box Optimization Using Affine Combinations and Shifts](https://mlsanity.com/paper/2312.11083/) (2023)
- [MetaDE: Evolving Differential Evolution by Differential Evolution](https://mlsanity.com/paper/2502.10470/) (2025)
- [Meta-Black-Box-Optimization through Offline Q-function Learning](https://mlsanity.com/paper/2505.02010/) (2025)
- [Automated Metaheuristic Algorithm Design with Autoregressive Learning](https://mlsanity.com/paper/2405.03419/) (2024)

## Built on by (most cited first, 6 of 6)

- [LLM Driven Design of Continuous Optimization Problems with Controllable High-level Properties](https://mlsanity.com/paper/2601.18846/) (2026)
- [Task-free Adaptive Meta Black-box Optimization](https://mlsanity.com/paper/2601.21475/) (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)
- [Reinforcement learning to choose optimizers](https://mlsanity.com/paper/2609.01811/) (2026)
- [Hyper Algorithm Design Agent: Evolving Learnable Optimizer from Zero](https://mlsanity.com/paper/2609.35328/) (2026)

## Abstract (arXiv)

To relieve intensive human-expertise required to design optimization algorithms, recent Meta-Black-Box Optimization (MetaBBO) researches leverage generalization strength of meta-learning to train neural network-based algorithm design policies over a predefined training problem set, which automates the adaptability of the low-level optimizers on unseen problem instances. Currently, a common training problem set choice in existing MetaBBOs is well-known benchmark suites CoCo-BBOB. Although such choice facilitates the MetaBBO's development, problem instances in CoCo-BBOB are more or less limited in diversity, raising the risk of overfitting of MetaBBOs, which might further results in poor generalization. In this paper, we propose an instance generation approach, termed as LSRE, which could generate diverse training problem instances for MetaBBOs to learn more generalizable policies. LSRE first trains an autoencoder which maps high-dimensional problem features into a 2-dimensional latent space. Uniform-grid sampling in this latent space leads to hidden representations of problem instances with sufficient diversity. By leveraging a genetic-programming approach to search function formulas with minimal L2-distance to these hidden representations, LSRE reverse engineers a diversified problem set, termed as Diverse-BBO. We validate the effectiveness of LSRE by training various MetaBBOs on Diverse-BBO and observe their generalization performances on either synthetic or realistic scenarios. Extensive experimental results underscore the superiority of Diverse-BBO to existing training set choices in MetaBBOs. Further ablation studies not only demonstrate the effectiveness of design choices in LSRE, but also reveal interesting insights on instance diversity and MetaBBO's generalization.