Jie Wu

Hi! I am Jie Wu, an M.S. student at Tsinghua University in the IIGroup, advised by Prof. Yujiu Yang.I work on the Qwen team, focusing on environment scaling, task synthesis, and scaffold adaptations for terminal agents (see Terminal Universe).
Besides, I also support web-based environment scaling for browser-use agents.

Internship

Education

Shenzhen International Graduate School · Shenzhen, China

GPA: 3.98/4.0 · Rank: 1/226 · Wuhan, China

Research Interests

My research centers on LLMs for Code and Agents, with a specific focus on:

Instruction Synthesis and Alignment

Exploring synthetic data generation and alignment.

Target-DPO EMNLP 2025 EpiCoder ICML 2025

Reasoning for Competitive Programming

Enhancing LLM reasoning for complex algorithmic challenges.

X-Coder Over 14K downloads EMNLP 2026

Environment Scaling for Agents

Scaling environments and synthesizing tasks for terminal, webdev, and browser-use agents.

Terminal-Universe Qwen Tech Report

Publications

Selected first-author work

Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments

Qwen Tech Report Paper

Jie Wu, Zhenru Zhang, Beichen Zhang, Xuwu Wang, Yuhui Su, Mouxiang Chen, Peng Wang, Zhihai Wang, Que Shen, Hao Zhou, An Yang, Fei Huang, Yujiu Yang, Dayiheng Liu

X-Coder: Advancing Competitive Programming with Fully Synthetic Tasks, Solutions, and Tests

EMNLP 2026 Main Paper Code Data Model

Jie Wu, Haoling Li, Xin Zhang, Jiani Guo, Jane Luo, Steven Liu, Yangyu Huang, Ruihang Chu, Scarlett Li, Yujiu Yang

Teaching Your Models to Understand Code via Focal Preference Alignment

EMNLP 2025 Main Paper Code

Jie Wu, Haoling Li, Xin Zhang, Xiao Liu, Yangyu Huang, Jianwen Luo, Yizhen Zhang, Zuchao Li, Ruihang Chu, Yujiu Yang, Scarlett Li

Leveraging Tree-oriented MapReduce for Long-Context Reasoning in Large Language Models

EMNLP 2025 Main Paper Code

Jiani Guo, Jie Wu, Zuchao Li, Qianren Wang, Yun Li, Lefei Zhang, Hai Zhao, Yujiu Yang

Multi-modal Fake News Detection via Decision Uncertainty

ACM MM 2024 Oral Paper Code

Jie Wu, Danni Xu, Wenxuan Liu, Joey Zhou, Yew Ong, Siyuan Hu, Hongyuan Zhu, Zheng Wang

Collaborative work

RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation

ICLR 2026 Paper Code

Jane Luo*, Xin Zhang*, Steven Liu, Jie Wu, Jianfeng Liu, Yiming Huang, Yangyu Huang, Chengyu Yin, Ying Xin, Yuefeng Zhan, Hao Sun, Qi Chen, Scarlett Li, Mao Yang

Closing the Loop: Universal Repository Representation with RPG-Encoder

ICML 2026 Paper Code

Jane Luo*, Chengyu Yin*, Xin Zhang*, Qingtao Li, Steven Liu, Yiming Huang, Jie Wu, Hao Liu, Yangyu Huang, Yu Kang, Fangkai Yang, Ying Xin, Scarlett Li

TestExplora: Benchmarking LLMs for Proactive Bug Discovery via Repository-Level Test Generation

ICML 2026 Paper Code

Steven Liu, Jane Luo, Xin Zhang, Aofan Liu, Hao Liu, Jie Wu, Ziyang Huang, Yangyu Huang, Yu Kang, Scarlett Li

EpiCoder: Encompassing Diversity and Complexity in Code Generation

ICML 2025 Paper Code

Yaoxiang Wang*, Haoling Li*, Xin Zhang*, Jie Wu, Xiao Liu, Wenxiang Hu, Zhongxin Guo, Yangyu Huang, Ying Xin, Yujiu Yang, Jinsong Su, Qi Chen, Scarlett Li

A.S.E: A Repository-Level Benchmark for Evaluating Security in AI-Generated Code

ACL 2026 Findings Paper Code

Keke Lian, Bin Wang, Lei Zhang, Libo Chen, Junjie Wang, Ziming Zhao, Yujiu Yang, Miaoqian Lin, Haotong Duan, Haoran Zhao, Shuang Liao, Mingda Guo, Jiazheng Quan, Yilu Zhong, Chenhao He, Zichuan Chen, Jie Wu, Haoling Li, Zhaoxuan Li, Jiongchi Yu, Hui Li, Dong Zhang