Lirui Luo

I am a Ph.D. student in the School of Intelligence at Peking University (PKU), majoring in Computer Science and Technology (Intelligent Science and Technology), advised by Cong Fang. I received my B.E. in Communication Engineering from the School of Electronic and Information Engineering at Beijing Jiaotong University (BJTU) in 2023.

I am also a long-term research intern at Beijing Institute for General Artificial Intelligence (BIGAI), affiliated with the Agent Learning Department and mentored by Dr. Qing Li and Dr. Guoxi Zhang.

My research focuses on continual reinforcement learning for agents that learn, adapt, and self-improve through long-term interaction. I study how reinforcement learning agents preserve plasticity, acquire new skills, and evolve across changing tasks and environments. Recently, I have also been exploring continual reinforcement learning for large models, including RLVR-style training and agent self-improvement.

news

May 05, 2026	SPHERE accepted by ICML 2026.
Jan 30, 2026	MVR accepted by ICLR 2026.
Jun 13, 2024	INSIGHT has been selected as a spotlight-designated paper.
May 22, 2024	INSIGHT accepted by ICML 2024.

experiences

Oct 01, 2022	Research intern at BIGAI

publications

ICML

SPHERE: Mitigating the Loss of Spectral Plasticity in Mixture-of-Experts for Deep Reinforcement Learning

Lirui Luo, Guoxi Zhang, Hongming Xu, and 2 more authors

In Proceedings of the 43rd International Conference on Machine Learning , 2026

Bib Code Website

@inproceedings{luo2026sphere,
  title = {SPHERE: Mitigating the Loss of Spectral Plasticity in Mixture-of-Experts for Deep Reinforcement Learning},
  author = {Luo, Lirui and Zhang, Guoxi and Xu, Hongming and Fang, Cong and Li, Qing},
  booktitle = {Proceedings of the 43rd International Conference on Machine Learning},
  year = {2026},
}

ICLR

MVR: Multi-view Video Reward Shaping for Reinforcement Learning

Lirui Luo, Guoxi Zhang, Hongming Xu, and 3 more authors

ICLR, 2026

Bib Code Website

@article{luo2026mvr,
  title = {MVR: Multi-view Video Reward Shaping for Reinforcement Learning},
  author = {Luo, Lirui and Zhang, Guoxi and Xu, Hongming and Yang, Yaodong and Fang, Cong and Li, Qing},
  journal = {ICLR},
  year = {2026},
}

ICML

End-to-End Neuro-Symbolic Reinforcement Learning with Textual Explanations

Lirui Luo, Guoxi Zhang, Hongming Xu, and 3 more authors

ICML, 2024

Bib Code Website

@article{luo2024insight,
  title = {End-to-End Neuro-Symbolic Reinforcement Learning with Textual Explanations},
  author = {Luo, Lirui and Zhang, Guoxi and Xu, Hongming and Yang, Yaodong and Fang, Cong and Li, Qing},
  journal = {ICML},
  year = {2024},
}