Junlin Yang

I build agents for digital and physical worlds—modeling the tasks they face, scaling how they learn and act, and pushing them toward self-evolution.

I'm a first-year PhD student in Tsinghua C3I Lab, advised by Ning Ding and Bowen Zhou.

Previously, I worked as a research intern at The University of Hong Kong with Prof. Tao Yu, and at the University of Illinois Urbana-Champaign with Prof. Hao Peng.

Feel free to reach out about research, collaborations, or just for a friendly chat.

Publications

Google Scholar

Autoresearch Agents

Frontis-MA1: Training an AI4AI Model towards Recursive Self-Improvement in Machine Learning Engineering

Junlin Yang*^†, Che Jiang*^†, Yu Fu*, Tianwei Luo*, Can Ren*, Weizhi Wang*, Kaikai Zhao*, Hongyi Liu, Yuxin Zuo, Yuru Wang, Yuchen Fan, Kai Tian, Zhenzhao Yuan, Xiaojian Lin, Li Sheng, Rushi Qiang, Guoli Jia, Xingtai Lv, Ermo Hua, Dianqiao Lei, Youbang Sun, Ning Ding, Bowen Zhou, Kaiyan Zhang^‡

* Core contributor · ^† Project leader · ^‡ Corresponding author

arXiv, 2026

Paper Daily Papers GitHub Models & Data Project Twitter

Also surfaced as OpenMLE, Frontis-MA1 is the first model release in the OpenRSI series: an open AI4AI stack for recursive self-improvement in machine learning engineering.

Digital Agents

OpenCUA: Open Foundations for Computer-Use Agents

Xinyuan Wang*, Bowen Wang*, Dunjie Lu*, Junlin Yang*, Tianbao Xie*, Junli Wang*, Jiaqi Deng, Xiaole Guo, Yiheng Xu, Chen Henry Wu, Zhennan Shen, Zhuokai Li, Ryan Li, Xiaochuan Li, Junda Chen, Boyuan Zheng, Peihang Li, Fangyu Lei, Ruisheng Cao, Yeqiao Fu, Dongchan Shin, Martin Shin, Jiarui Hu, Yuyan Wang, Jixuan Chen, Yuxiao Ye, Danyang Zhang, Dikang Du, Hao Hu, Huarong Chen, Zaida Zhou, Yipu Wang, Heng Wang, Diyi Yang, Victor Zhong, Flood Sung, Y. Charles, Zhilin Yang, Tao Yu

* Equal contribution

NeurIPS 2025 Spotlight · COLM 2025 AIA Workshop Best Paper

Paper Project Code

Open data, tooling, and foundation models for scaling computer-use agents across operating systems and real applications.

Digital Agents

Scaling Computer-Use Grounding via User Interface Decomposition and Synthesis

Tianbao Xie*, Jiaqi Deng*, Xiaochuan Li*, Junlin Yang*, Haoyuan Wu, Jixuan Chen, Wenjing Hu, Xinyuan Wang, Yuhui Xu, Zekun Wang, Yiheng Xu, Junli Wang, Doyen Sahoo, Tao Yu, Caiming Xiong

* Equal contribution

NeurIPS 2025 Datasets & Benchmarks Track Spotlight

Paper Project Code

A scalable recipe for grounding computer-use agents through realistic UI decomposition, synthesis, and four million training examples.

Self-Evolving Agents

Self-Improving Agents in the Era of Experience: A Survey of Self- to Meta-Evolution

Che Jiang*^†, Jincheng Zhong*, Yu Fu*, Kai Tian*, Junlin Yang*, Kaikai Zhao*, Yuchong Wang*, Tianwei Luo*, Weizhi Wang, Yuxin Zuo, Guoli Jia, Xingtai Lv, Dianqiao Lei, Sihang Zeng, Yuru Wang, Zhenzhao Yuan, Xinwei Long, Ermo Hua, Can Ren, Xin Jiang, Shulei Xie, Yuanchun Zheng, Youbang Sun, Biqing Qi, Ning Ding^‡, Kaiyan Zhang^†‡, Bowen Zhou^‡

* Core contributor · ^† Project leader · ^‡ Corresponding author

OpenReview Archive, 2026

Paper Project Paper List

A map of how deployment experience becomes reusable skills, persistent memory, parameter updates, and ultimately meta-evolution.

Autoresearch Agents

CausaLab: A Scalable Environment for Interactive Causal Discovery Toward AI Scientists

Junlin Yang*, Dylan Zhang*, Xiangchen Song, Qirun Dai, Xiao Liu, Yuen Chen, Aniket Vashishtha, Jing Shi, Chenhao Tan, Hao Peng

* Equal contribution

arXiv, 2026

Paper Project Code

A synthetic laboratory that tests whether agents can discover causal mechanisms by choosing experiments—not merely predict the right answer.

ICLR 2026

Scalable LLM Learning

How Far Can Unsupervised RLVR Scale LLM Training?

Bingxiang He*, Yuxin Zuo*, Zeyuan Liu*, Shangziqi Zhao*, Zixuan Fu, Junlin Yang, Cheng Qian, Kaiyan Zhang, Yuchen Fan, Ganqu Cui, Xiusi Chen, Youbang Sun, Xingtai Lv, Xuekai Zhu, Li Sheng, Ran Li, Huan-ang Gao, Yuchen Zhang, Lifan Yuan, Bowen Zhou^‡, Zhiyuan Liu^‡, Ning Ding^‡

* Equal contribution · ^‡ Corresponding author

Paper Scholar

ICLR 2026

Digital Agents

VideoAgentTrek: Computer Use Pretraining from Unlabeled Videos

Dunjie Lu, Yiheng Xu, Junli Wang, Haoyuan Wu, Xinyuan Wang, Zekun Wang, Junlin Yang, Hongjin Su, Jixuan Chen, Junda Chen, Yuchen Mao, Jingren Zhou, Junyang Lin, Binyuan Hui, Tao Yu

Paper Scholar

arXiv 2026

Autoresearch Agents

MLS-Bench: A Holistic and Rigorous Assessment of AI Systems on Building Better AI

Bohan Lyu, Yucheng Yang, Siqiao Huang, Jiaru Zhang, Qixin Xu, Xinghan Li, Xinyang Han, Yicheng Zhang, Huaqing Zhang, Runhan Huang, Kaicheng Yang, Zitao Chen, Wentao Guo, Junlin Yang, Xinyue Ai, Wenhao Chai, Yadi Cao, Ziran Yang, Kun Wang, Dapeng Jiang, Huan-ang Gao, Shange Tang, Chengshuai Shi, Simon S. Du, Max Simchowitz, Jiantao Jiao, Dawn Song, Chi Jin

Paper Project Scholar

arXiv 2026

Autoresearch Agents

NatureBench: Can Coding Agents Match the Published SOTA of Nature-Family Papers?

Yuru Wang, Lejun Cheng, Yuxin Zuo, Sihang Zeng, Bingxiang He, Che Jiang, Junlin Yang, Yuchong Wang, Kaikai Zhao, Weifeng Huang, Kai Tian, Zhenzhao Yuan, Jincheng Zhong, Weizhi Wang, Ning Ding^‡, Bowen Zhou^‡, Kaiyan Zhang^‡

^‡ Corresponding author

Paper Code Scholar

arXiv 2026

Scalable LLM Learning

Post-Trained MoE Can Skip Half Experts via Self-Distillation

Xingtai Lv*, Li Sheng*, Kaiyan Zhang*, Yichen You, Siyan Gao, Xueheng Luo, Yuxin Zuo, Yuchen Fan, Junlin Yang, Ganqu Cui, Bingning Wang, Fan Yang, Youbang Sun^‡, Ning Ding^‡, Bowen Zhou^‡

* Equal contribution · ^‡ Corresponding author

Paper Code Scholar

Selected Awards and Honors

2026Excellent Graduate, Tsinghua University
2023–2025Overall Excellence Scholarship, Tsinghua University
2023Outstanding Student Cadre, Tsinghua University
2022Freshman Scholarship, Tsinghua University

Service and Leadership

Chi Mu Zhi Jie (尺木之阶)

I founded the first alumni mutual-help platform at Shenzhen Experimental High School. It bridges information gaps around university life and has reached 50K+ reads and 2.5K+ followers.