Yuxing Wang (王昱兴)

您好 · Привет · Hello · Bonjour · Ciao · こんにちは · 안녕하세요 · Hallo · Hola

Designing machines that design machines.

I am Yuxing Wang, a researcher working on Embodied Co-Design, Robot Learning, and Agentic AI.

My work is driven by a fascination with systems that can move, adapt, and eventually participate in their own design. I study how learning algorithms, physical morphology, and environmental structure can be optimized together, so embodied agents are not only structurally feasible but behaviorally capable.

Cartoon illustration of a robot design loop

Biography

I earned my B.Eng. from Southwest Minzu University in 2020 and my M.Eng. from Tsinghua University in 2023, advised by Prof. Xueqian Wang. I am now pursuing a Ph.D. in Control Science and Engineering at Tsinghua.

During my 2022-2023 research internship at Tencent AI Lab, supported by the Tencent Rhino-Bird Research Elite Program, I worked with Shuang Wu and Haobo Fu on user-specified behavioral diversity for Game AI.

Research Style

I like research that is visual, physical, and a little stubborn: systems should move, fail, improve, and eventually reveal a design principle.

Outside the lab, I recharge with Hikaru Utada, comedies, and talk shows.

News

May 30, 2026	One paper was accepted to PPSN 2026.
Mar 21, 2026	One paper was accepted to GECCO 2026.
Dec 01, 2025	Our survey “Embodied Co-Design for Rapidly Evolving Agents: Taxonomy, Frontiers, and Challenges” is publicly available on arXiv!
Aug 01, 2025	Served as a reviewer for ICLR 2026 and AAAI 2026.
May 01, 2025	Two papers were accepted to the International Astronautical Congress (IAC) 2025. See you in Sydney, Australia!
Mar 10, 2025	Served as a program committee member for NeurIPS 2025 and ACM MM 2025.
Jan 01, 2025	A website for our survey “Embodied Co-Design for Rapidly Evolving Agents: Taxonomy, Frontiers, and Challenges” has been created. The repo will be updated on a regular basis! The full paper will be posted to arXiv soon!

Report

MIT Technology Review China coverage

我设计我自己！清华最新研究：未来机器人不用人设计，AI直接捏出最优形态

Read report

Selected Works

ModularEvoGym

A co-design benchmark and methods for modular soft robot morphology and control.

SurveyBrainBody

A living survey on taxonomy, frontiers, and challenges in embodied co-design.

Surrogate-assisted ERL

Reducing expensive controller search with learned fitness estimation.

Selected Publications

PPSN

Enhancing Quality-Diversity with Adaptive Heterogeneous Operator Allocation

Xinyang Li, Yuxing Wang^*, Xueqian Wang, and Houde Liu

Parallel Problem Solving From Nature (PPSN), 2026

CCF B Bib

Poster

@article{li2026,
  title = {Enhancing Quality-Diversity with Adaptive Heterogeneous Operator Allocation},
  author = {Li, Xinyang and Wang, Yuxing and Wang, Xueqian and Liu, Houde},
  journal = {Parallel Problem Solving From Nature},
  year = {2026},
}

GECCO

Surrogate-Assisted Evolutionary Multi-Agent Reinforcement Learning with Adaptive Fitness Evaluation

Cong Yu, Yuxing Wang^*, Xinyang Li, and Xueqian Wang

Genetic and Evolutionary Computation Conference (GECCO), 2026

CCF C Bib

Poster

@article{yu2026surrogate,
  title = {Surrogate-Assisted Evolutionary Multi-Agent Reinforcement Learning with Adaptive Fitness Evaluation},
  author = {Yu, Cong and Wang, Yuxing and Li, Xinyang and Wang, Xueqian},
  journal = {Genetic and Evolutionary Computation Conference},
  year = {2026},
}

Survey

Embodied Co-Design for Rapidly Evolving Agents: Taxonomy, Frontiers, and Challenges

Yuxing Wang, Zhiyu Chen, Tiantian Zhang, Qiyue Yin, Yongzhe Chang, Zhiheng Li, Liang Wang, and Xueqian Wang

arXiv (Survey), 2025

Preprint arXiv Bib HTML

Submitted to IEEE TEVC

@article{wang2025survey,
  title = {Embodied Co-Design for Rapidly Evolving Agents: Taxonomy, Frontiers, and Challenges},
  author = {Wang, Yuxing and Chen, Zhiyu and Zhang, Tiantian and Yin, Qiyue and Chang, Yongzhe and Li, Zhiheng and Wang, Liang and Wang, Xueqian},
  journal = {arXiv},
  year = {2025},
}

IAC

Morphology and Behavior Co-Optimization of Modular Satellites for Attitude Control

Yuxing Wang, Jie Li, Cong Yu, Xinyang Li, Simeng Huang, Yongzhe Chang, Xueqian Wang, and Bin Liang

The 75th International Astronautical Congress (IAC), 2024

EI arXiv Bib

Top conference, Oral Presentation

@article{wang2024morphology,
  title = {Morphology and Behavior Co-Optimization of Modular Satellites for Attitude Control},
  author = {Wang, Yuxing and Li, Jie and Yu, Cong and Li, Xinyang and Huang, Simeng and Chang, Yongzhe and Wang, Xueqian and Liang, Bin},
  journal = {The 75th International Astronautical Congress},
  year = {2024},
}

TNNLS

Dynamics-adaptive continual reinforcement learning via progressive contextualization

Tiantian Zhang, Zichuan Lin, Yuxing Wang, Deheng Ye, Qiang Fu, Wei Yang, Xueqian Wang, Bin Liang, Bo Yuan, and Xiu Li

IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2023

JCR Q1, CCF B arXiv Bib HTML Code

SCI Journal, IF=10.4

@article{zhang2023dynamics,
  title = {Dynamics-adaptive continual reinforcement learning via progressive contextualization},
  author = {Zhang, Tiantian and Lin, Zichuan and Wang, Yuxing and Ye, Deheng and Fu, Qiang and Yang, Wei and Wang, Xueqian and Liang, Bin and Yuan, Bo and Li, Xiu},
  journal = {IEEE Transactions on Neural Networks and Learning Systems},
  year = {2023},
  publisher = {IEEE},
}

CoRL

PreCo: Enhancing Generalization in Co-Design of Modular Soft Robots via Brain-Body Pre-Training

Yuxing Wang, Shuang Wu, Tiantian Zhang, Yongzhe Chang, Haobo Fu, Qiang Fu, and Xueqian Wang

In Conference on Robot Learning (CoRL) , 2023

EI, Oral Presentation, top 6.6% Bib HTML Code

Top conference

@inproceedings{wang2023preco,
  title = {PreCo: Enhancing Generalization in Co-Design of Modular Soft Robots via Brain-Body Pre-Training},
  author = {Wang, Yuxing and Wu, Shuang and Zhang, Tiantian and Chang, Yongzhe and Fu, Haobo and Fu, Qiang and Wang, Xueqian},
  booktitle = {Conference on Robot Learning},
  pages = {478--498},
  year = {2023},
  organization = {PMLR},
}

ICLR

Curriculum-based co-design of morphology and control of voxel-based soft robots

Yuxing Wang, Shuang Wu, Haobo Fu, Qiang Fu, Tiantian Zhang, Yongzhe Chang, and Xueqian Wang

In The Eleventh International Conference on Learning Representations (ICLR) , 2023

CCF A, Poster Bib HTML Code

Top conference

@inproceedings{wang2023curriculum,
  title = {Curriculum-based co-design of morphology and control of voxel-based soft robots},
  author = {Wang, Yuxing and Wu, Shuang and Fu, Haobo and Fu, Qiang and Zhang, Tiantian and Chang, Yongzhe and Wang, Xueqian},
  booktitle = {The Eleventh International Conference on Learning Representations},
  year = {2023},
}

InS

A surrogate-assisted controller for expensive evolutionary reinforcement learning

Yuxing Wang, Tiantian Zhang, Yongzhe Chang, Xueqian Wang, Bin Liang, and Bo Yuan

Information Sciences (InS), 2022

JCR Q1, CCF B arXiv Bib HTML Code

SCI Journal, IF=8.233

@article{wang2022surrogate,
  title = {A surrogate-assisted controller for expensive evolutionary reinforcement learning},
  author = {Wang, Yuxing and Zhang, Tiantian and Chang, Yongzhe and Wang, Xueqian and Liang, Bin and Yuan, Bo},
  journal = {Information Sciences},
  volume = {616},
  pages = {539--557},
  year = {2022},
  publisher = {Elsevier},
}