About
Hello! I’m a PhD student at the University of Science and Technology of China (USTC), co-advised by Dr. Lei Bai and Prof. Wengang Zhou. My research interests are LLM Post-training, Agent and AI Infra. I earned my BSc in Computer Science from USTC, and was a Master’s student there before transferring to the PhD in Fall 2025. I am currently interning at Shanghai AI Lab, mentored by Dr. Chen Zhang and Dr. Shuyue Hu.
Feel free to reach out via email. You can also find me on Zhihu and Xiaohongshu.
News
We released SKT, a verified synthetic-data pipeline for training language-model agents to identify, apply, and coordinate reusable skills at scale.
We released Agents-A1, an open 35B MoE agent model that scales the interaction horizon for long-horizon search, engineering, and scientific reasoning, as a public technical report.
We released PAPO, a reinforcement-learning method that integrates rubric-based process supervision through decoupled advantage normalization. Accepted to the EMNLP 2026 Main Conference.
We launched AgentPanel, a multi-agent forum for human-AI collaboration in exploring scientific questions. Accepted to DAI 2026 as an oral presentation.
We released SkillsBench, a benchmark for measuring how well Agent Skills work across diverse, expertise-heavy tasks. Accepted to NeurIPS 2026.
I joined Shanghai AI Laboratory as a research intern, mentored by Dr. Chen Zhang and Dr. Shuyue Hu.
We released Scaling Laws for LLM Reinforcement Learning. Accepted to the ACL 2026 Main Conference.
I transferred from the Master’s program into the PhD program at USTC and began my doctoral studies, co-advised by Dr. Lei Bai and Prof. Wengang Zhou.
I joined Meituan as an AI Infra intern, mentored by Yineng Zhang and Ke Bao.
We released libsmctrl, a runtime library for SM-level GPU compute partitioning and operator isolation.
I joined Tencent as an AI Infra intern working on LLM inference acceleration, mentored by Hande Dong.