About me

I am Qijia He, a first-year Ph.D. student in the Department of Electrical and Computer Engineering at The Ohio State University, advised by Prof. Yingbin Liang. I received my bachelor degree from the Southern University of Science and Technology (SUSTech), where I was advised by Prof. Fang Kong and Prof. Yifang Ma. In 2023, I spent a semester as an exchange student at Stony Brook University. My research interests include bandit algorithms and reinforcement learning for large language models.

Publication

• Provable Test-Time Scaling for Beam Search in LLM Reasoning (NeurIPS 2026)
  • Qijia He*, Yu Huang*, Yuan Cheng*, Yuxin Chen, Yingbin Liang.
• PACT: Privileged Trace Co-Training for Multi-Turn Tool-Use Agents (Preprint)
  • Zhenbang Du*, Jun Luo*, Zhiwei Zheng, Xiangchi Yuan, Kejing Xia, Dachuan Shi, Qirui Jin, Qijia He, Shaofeng Zou, Yingbin Liang, Wenke Lee.
• Learning Across the Gap: Hybrid Multi-armed Bandits with Heterogeneous Offline and Online Data (NeurIPS 2025)
  • Qijia He, Minghan Wang, Xutong Liu, Zhiyong Wang, and Fang Kong.