Kaiyan Zhang (张开颜)

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 research centers on the alignment and collaboration of large language models (LLMs), with the broader goal of building scalable collaborative intelligence systems. I am currently developing an LLM-based multi-agent reinforcement learning framework to enhance reasoning capabilities beyond foundational levels (R1 and O1). My work also explores how multiple agents can effectively collaborate on real-world, agentic tasks.

I am open to collaborations and discussions across related areas—such as multi-agent (COLM 2024, ACL 2024, Arxiv 2406), reinforcement learning (Arxiv 2412 - ImplicitPRM, Arxiv 2502 - PRIME), test-time scaling (ICLR 2025 - OpenPRM, Arxiv 2502, Arxiv 2503 - Video-T1, Arxiv 2504 - GenPRM), test-time reinforcement learning (Arxiv 2504 - TTRL), and multi-agent reinforcement learning (GitHub 2025 - MARTI). I’d be happy to connect with researchers who share these interests.