Yuxiang Wei

About

I am a PhD candidate at UIUC CS, advised by Lingming Zhang. I was also a student researcher at Meta FAIR from 2024–2025, working at the CodeGen/CodeLlama team.

I train code agents.

Research

Research impact: I lead Self-Play SWE-RL (SSR), SWE-RL (NeurIPS’25), Magicoder (ICML’24), and SelfCodeAlign (NeurIPS’24), projects that have captured broad attention and are widely adopted across industry and open source.

New: We released Self-Play SWE-RL (SSR), which trains a single LLM agent to self-improve by self-playing between bug-injection and bug-repair, grounded in real-world repositories, no human-labeled issues or tests.

Publications

Preprint | Toward Training Superintelligent Software Agents Through Self-Play SWE-RL
Yuxiang Wei, Zhiqing Sun, Emily McMilin, Jonas Gehring, David Zhang, Gabriel Synnaeve, Daniel Fried, Lingming Zhang, and Sida Wang
https://arxiv.org/abs/2512.18552. 2025
Preprint | Live-SWE-Agent: Can Software Engineering Agents Self-Evolve on the Fly?
Chunqiu Steven Xia, Zhe Wang, Yan Yang, Yuxiang Wei, and Lingming Zhang
https://arxiv.org/abs/2511.13646. 2025
Tech Report | CWM: An Open-Weights LLM for Research on Code Generation with World Models
Meta FAIR CodeGen Team. Yuxiang Wei — Core contributor
https://ai.meta.com/research/publications/cwm/. 2025
NeurIPS’25 | SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution
Yuxiang Wei, Olivier Duchenne, Jade Copet, Quentin Carbonneaux, Lingming Zhang, Daniel Fried, Gabriel Synnaeve, Rishabh Singh, and Sida Wang
The Thirty-Ninth Annual Conference on Neural Information Processing Systems. https://openreview.net/forum?id=ULblO61XZ0. 2025
NeurIPS’25 | PurpCode: Reasoning for Safer Code Generation
Jiawei Liu, Nirav Diwan, Zhe Wang, Haoyu Zhai, Xiaona Zhou, Kiet A. Nguyen, Tianjiao Yu, Muntasir Wahed, Yinlin Deng, Hadjer Benkraouda, Yuxiang Wei, et al.
The Thirty-Ninth Annual Conference on Neural Information Processing Systems. https://openreview.net/forum?id=VUoY5kacG5. 2025
NeurIPS’24 | SelfCodeAlign: Self-Alignment for Code Generation
Yuxiang Wei, Federico Cassano, Jiawei Liu, Yifeng Ding, Naman Jain, Zachary Mueller, Harm de Vries, Leandro Von Werra, Arjun Guha, and Lingming Zhang
The Thirty-Eighth Annual Conference on Neural Information Processing Systems. https://openreview.net/forum?id=xXRnUU7xTL. 2024
DL4C@ICLR’25 | Arctic-SnowCoder: Demystifying High-Quality Data in Code Pretraining
Yuxiang Wei, Hojae Han, and Rajhans Samdani
ICLR 2025 Third Workshop on Deep Learning for Code. https://openreview.net/forum?id=lP44oj9cWU. 2025
COLM’24 | Evaluating Language Models for Efficient Code Generation
Jiawei Liu, Songrun Xie, Junhao Wang, Yuxiang Wei, Yifeng Ding, and Lingming Zhang
First Conference on Language Modeling. https://openreview.net/forum?id=IBCBMeAhmC. 2024
LCFM@ICML’24 | RepoQA: Evaluating Long Context Code Understanding
Jiawei Liu, Jia Le Tian, Vijay Daita, Yuxiang Wei, Yifeng Ding, Yuhan Katherine Wang, Jun Yang, and Lingming Zhang
First Workshop on Long-Context Foundation Models @ ICML 2024. https://openreview.net/forum?id=hK9YSrFuGf. 2024
Tech Report | StarCoder 2 and the Stack V2: The Next Generation
Anton Lozhkov, Raymond Li, Loubna Ben Allal, Federico Cassano, Joel Lamy-Poirier, Nouamane Tazi, Ao Tang, Dmytro Pykhtar, Jiawei Liu, Yuxiang Wei, Tianyang Liu, et al.
https://arxiv.org/abs/2402.19173. 2024
ACL’24 | XFT: Unlocking the Power of Code Instruction Tuning by Simply Merging Upcycled Mixture-of-Experts
Yifeng Ding, Jiawei Liu, Yuxiang Wei, and Lingming Zhang
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). https://aclanthology.org/2024.acl-long.699. 2024
ICML’24 | Magicoder: Empowering Code Generation with OSS-Instruct
Yuxiang Wei, Zhe Wang, Jiawei Liu, Yifeng Ding, and Lingming Zhang
Proceedings of the 41st International Conference on Machine Learning. https://proceedings.mlr.press/v235/wei24h.html. 2024
ESEC/FSE’23 | Copiloting the Copilots: Fusing Large Language Models with Completion Engines for Automated Program Repair
Yuxiang Wei, Chunqiu Steven Xia, and Lingming Zhang
Proceedings of the 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering. https://doi.org/10.1145/3611643.3616271. 2023
ICSE’23 | Automated Program Repair in the Era of Large Pre-Trained Language Models
Chunqiu Steven Xia, Yuxiang Wei, and Lingming Zhang
Proceedings of the 45th International Conference on Software Engineering. https://doi.org/10.1109/ICSE48619.2023.00129. 2023
OOPSLA’22 | Coverage-Guided Tensor Compiler Fuzzing with Joint IR-Pass Mutation
Jiawei Liu, Yuxiang Wei, Sen Yang, Yinlin Deng, and Lingming Zhang
Proc. ACM Program. Lang. https://doi.org/10.1145/3527317. 2022

Awards and Honors

Invited Talks