We are a research team that mainly focuses on the advanced optimization techniques such as Evolutionary Computation, Reinforcement Learning-assisted Optimization, Meta Black Box Optimization and Foundational Optimization Agents. The founders of MetaEvo includes professors from South China University of Technology (SCUT) and South China Normal University (SCNU). This is an energetic team including undergraduate students, master students and phd students. The student leader in this team is Wenjie Qiu, persuing his PhD degree at SCUT. Students in MetaEvo team are advised (in part advised) by Prof. Yue-Jiao Gong, Prof. Zeyuan Ma and Prof. Hongshu Guo. As a pure research-oriented technical team, we aim to develop the new generation of black-box-optimization concepts, algorithms, frameworks and benchmarks. The resulting research domain is commonly termed as Meta-Black-Box-Optimization (MetaBBO), which generally mitigates the labour-intensive development in low-level black-box optimization algorithms through meta-learning automated algorithm design rules at meta level. We believe works done by this team could promote the research edge of both Evolutionary Computation and Optimization.

1. "MetaBox: A Benchmark Platform for Meta-Black-Box Optimization with Reinforcement Learning." Advances in Neural Information Processing Systems 36 (NeurIPS 2023, Oral).
2. "Symbol: Generating Flexible Black-Box Optimizers through Symbolic Equation Learning" (ICLR 2024).
3. "Auto-configuring Exploration-Exploitation Tradeoff in Evolutionary Computation via Deep Reinforcement Learning" The Genetic and Evolutionary Computation Conference (GECCO 2024).
4. "Toward Automated Algorithm Design: A Survey and Practical Guide to Meta-Black-Box-Optimization." IEEE Transactions on Evolutionary Computation (TEVC) (2025).
5. "Deep Reinforcement Learning for Dynamic Algorithm Selection: A Proof-of-Principle Study on Differential Evolution" IEEE Transactions on Systems, Man, and Cybernetics: Systems (TSMC) (2024).
6. "ConfigX: Modular Configuration for Evolutionary Algorithms via Multitask Reinforcement Learning" (AAAI 2025, Oral).
7. "Neural Exploratory Landscape Analysis for Meta-Black-Box-Optimization" (ICLR 2025).
8. "Meta-Black-Box-Optimization through Offline Q-function Learning" (ICML 2025).
9. "MetaBox-v2: A Unified Benchmark Platform for Meta-Black-Box Optimization" (NeurIPS 2025).
10. "DesignX: Human-Competitive Algorithm Designer for Black-Box Optimization" (NeurIPS 2025).
11. "Instance Generation for Meta-Black-Box Optimization through Latent Space Reverse Engineering" (AAAI 2026).

Feel free to discuss with us!

We are available on E-mail: 1、scut.crazynicolas@gmail.com 2、wukongqwj@gmail.com

We warmly invite you to join our QQ group for further communication (Group Number: 952185139).