PhD Student in AI 🔮
Hi! I’m Yifan Zeng and my name in Chinese is 曾一凡. I’m a fourth-year Computer Science Ph.D. student at Oregon State University, advised by Huazheng Wang.
My research is on reinforcement learning for LLM agents: training multi-turn, tool-using agents with online RL (GRPO/PPO on verl), understanding when RL helps multi-agent LLM workflows, and making agents and LLM rankers robust.
In summer 2026 I was a Research Scientist Intern at Adobe, where I built SkillSaw, a training-free method for optimizing agent skill libraries. Before that I was an AI Agent Research Intern at AG2AI (2025), and before my Ph.D. I worked on deep learning and computer vision in industry. I received my B.Eng. in Data Science from Zhuhai College of Jilin University in 2023 (GPA 3.84/4.00, rank 1/249).
I'm looking for Summer 2027 research / ML engineering internships on LLM agents and post-training (Ph.D. expected Spring 2028). CV / Resume (PDF)
Loading publications…
✧ Equal Contribution / Leading Contributors
The papers listed are sorted by the completion date of the initial version.