Hi! I’m building agentic AI systems for industrial R&D at scale, with a focus on:
- Super-Long-Horizon Agents: developing harness to orchestrate hundreds of agents for weeks-long R&D tasks involving thousands of compute jobs;
- Self-Improving Agents: enabling agents to learn from self/human feedback and reuse accumulated knowledge on new tasks; and
- Agent Observability: designing infrastructure for traceable, auditable, and resumable long-horizon agent task execution.
Beyond these areas, I work on reliable LLM/VLM reasoning, data-centric AI, and automated data mining. I was fortunate to be advised by Prof. Hanghang Tong (Ph.D. at UIUC) and Prof. Yi Chang (M.Eng. at
JLU). I also work closely with researchers from industry research labs including
Amazon Science,
Microsoft Research,
Google DeepMind,
Meta, and
IBM Research. I’m always happy to chat and discuss potential collaborations. Reach me via: WeChat (ZhiningLiuCS) or zhining.liu AT outlook.com.
Learn more about me😎:
- 🌏 Personal Page: https://zhiningliu.com
- 🎓 Google Scholar: https://scholar.google.com/citations?user=5WORAUQAAAAJ
- 💼 Linkedin: https://www.linkedin.com/in/zhiningliu
- 🍻 知乎/Zhihu: https://www.zhihu.com/people/liu-zhi-zhu-14
- 🎮 Steam: https://steamcommunity.com/id/zhiningliu1998
- 📬 Email me at: zhining.liu@outlook.com
| 🛸Featured Projects | |
|
🧠Awesome Agentic Reasoning Papers
[Awesome / Survey] [PDF] [arXiv] [Slides] [Hugging Face] |
![]() |
|
⚒️IMBENS: Ensemble Class-Imbalanced Learning in Python
[Python Library] [PDF] [CLIMB / NeurIPS'25] [Documentation] [Gallery] [PyPI] [Changelog] [Zhihu/知乎] |
|
|
⚖️Self-Paced Ensemble for Highly Imbalanced Massive Data Classification
[ICDE'20] [PDF] [arXiv] [Video] [Zhihu/知乎] |
|
|
😎Awesome-Imbalanced-Learning: a curated list of imbalanced learning resources
[Awesome] [English] [Chinese/中文] [Zhihu/知乎] |
|
|
😎Awesome Machine Learning Resources: a curated list across machine learning topics
[Awesome] [English] [Chinese/中文] [Zhihu/知乎] |
![]() |
| Github Stats | |
|
|
|





