Skip to content
View goodmanpzh's full-sized avatar
  • University of Science and Technology of China
  • University of Science and Technology of China

Block or report goodmanpzh

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
goodmanpzh/README.md

Hi there, I'm Zhihong Pan (潘志宏) 👋

USTC Research

🌐 Personal Homepage: goodmanpzh.github.io  |  📧 Email: [email protected]


👋 About Me

I am a third-year Master's student (since Sept. 2024) at the School of Artificial Intelligence and Data Science, University of Science and Technology of China (USTC), advised by A/Res. Kai Zhang (张凯). Before that, I received my B.E. in Data Science and Big Data Technology from Northeastern University.

🔬 Research interests: terminal coding agents · agent harness · efficient LLM inference · recommender systems / generative recommendation

🤝 I'm always open to discussion and collaboration — feel free to reach out via email 😃


🎓 Education

USTC University of Science and Technology of China (USTC)
M.S. in Computer Technology, School of Artificial Intelligence and Data Science
Sept. 2024 – Present · Advisor: Kai Zhang
NEU Northeastern University
B.E. in Data Science and Big Data Technology
Sept. 2020 – June 2024

💼 Experience

LongCat Meituan, LongCat Team · Research Intern
Coding Agent Post-training
Nov. 2025 – Sep. 2026

📝 Publications

  • Meta-Task: Turning Terminal Task Synthesis into a Terminal Task for Scalable Agent Training Zhihong Pan, Jiyuan He, Kai Zhang, Yupeng Han, Ze Liu, Yuze Zhao, Yongcong Ye, Zhaohua Yang arXiv preprint arXiv:2607.27929, 2026 · 📄 arXiv · 💻 Code · Ⓜ️ Model

  • Adaptive Model and Strategy Routing for Cost-Efficient LLM Services Zhihong Pan, Kai Zhang, Yuze Zhao, Yupeng Han ACM Web Conference (WWW), 2026 · 📄 PDF · 💻 Code

  • SimCDR: Preserving Intra-Domain Similarities of Users for Cross-Domain Recommendation Kai Zhang, Zhihong Pan, Lei Yu, Qi Liu, Hongke Zhao, Chaochao Chen, Enhong Chen ACM Transactions on Information Systems (TOIS) · 📄 PDF

  • Trust, but Verify: Uncertainty-Driven Evidential Multimodal Representation Learning Yupeng Han, Kai Zhang, Xianquan Wang, Zhihong Pan, Ze Liu, Jiyuan He International Joint Conference on Artificial Intelligence (IJCAI), 2026 · 📄 PDF

Pinned Loading

  1. Awesome-LLM-SWE-Research Awesome-LLM-SWE-Research Public

    A curated list of research papers, benchmark, frameworks, and resources related to SWE-bench and large language models for software engineering.

    4

  2. anomalyco/opencode anomalyco/opencode Public

    The open source coding agent.

    TypeScript 227k 30.7k

  3. harbor_mine harbor_mine Public

    Forked from harbor-framework/harbor

    Harbor is a framework for running agent evaluations and creating and using RL environments.

    Python