Kaiyan Zhang

I am a third-year PhD student at the Department of Electronic Engineering, Tsinghua University, under the guidance of Professor Bowen Zhou. I previously earned a Master’s degree in Computer Science and Technology in 2022 from the Harbin Institute of Technology (HIT), where I was supervised by Weinan Zhang and Ting Liu in the HIT-SCIR lab.

My primary research interests focus on the alignment and collaboration of large language models (LLMs), aiming to develop trustworthy and scalable collaborative intelligence systems. I am currently focused on developing LLM-based multi-agent reinforcement training framework aimed at advancing reasoning capabilities beyond basic levels (R1 and O1). My research also explores improving collaboration among agents in real-world, agentic tasks.

I am open to potential collaborations and discussions on these topics (like multi-agent in COLM 2024 / ACL 2024 / Arxiv 2406, reinforcement learning in Arxiv 2412 / Arxiv 2502, test-time scaling in ICLR 2025 / Arxiv 2502 / Arxiv 2503 / Arxiv 2504, and more) and would be glad to connect with others who share similar interests.