Tianjie Zhang   张天杰

tianjiez [at] cs [dot] cmu [dot] edu

I'm a master's student in the Machine Learning Department at Carnegie Mellon University, expected to graduate in December 2026. I received my bachelor's degree with honors in Computer Science and Technology from Zhejiang University.

My interest lies in large language models and language agents. Previously, I was a research associate member at Sea AI Lab, fortunate to be advised by Longxu Dou and Min Lin. I worked on agents that interact with computers via terminal environments.

From January 2024 to July 2024, I enjoyed a wonderful time at THUKEG, working with Professor Jie Tang and Yuxiao Dong on vision language model agents. During my undergraduate studies, I was also fortunate to be advised by Professor Yang Yang.

Resume   /   GitHub   /   LinkedIn   /   Google Scholar   /   X

Experience

From March 2025 to August 2025, I was a research associate member at Sea AI Lab, advised by Longxu Dou and Min Lin. We released Reptile, an LLM-based terminal agent. My primary focus was on agent scaffolding, human-in-the-loop training data collection and benchmarking.

From January 2024 to July 2024, I was a research intern at THUKEG, collaborating closely with Xiao Liu and Yu Gu, under the supervision of Professor Jie Tang and Yuxiao Dong. We released VisualAgentBench, a systematic benchmark to evaluate and develop vision language models as visual foundation agents. It has received over 70 citations and garnered .

Prior to that, I worked on enhancing the graph reasoning ability of large language models with Ziwei Chai, under the supervision of Professor Yang Yang. We proposed GraphLLM, which enables large language models to solve fundamental graph reasoning tasks with near-perfect accuracy. It has received over 170 citations and garnered .

Publications

* denotes equal contribution.

 ,  Credits