Jiahe Jin

Hi 👋 I'm an incoming Ph.D. student at LTI at Carnegie Mellon University. I received my B.Eng. in Computer Science from ACM Honors Class at Shanghai Jiao Tong University.

During my undergraduate years, I was fortunate to work with Prof. Chenyan Xiong at CMU, and with Prof. Pengfei Liu at SJTU.

I'm currently interested in continual learning and recursive self improvement, particularly how to enable learning over an infinite context.

Email: jjiahe [at] andrew [dot] cmu [dot] edu.

CV  /  Google Scholar  /  Github  /  Twitter

profile photo

News

Selected Publications     (Click here for all)
(* indicates equal contribution)
profile photo Beneficial Reasoning Behaviors in Agentic Search and Effective Post-training to Obtain Them
Jiahe Jin, Abhijay Paladugu, Chenyan Xiong
Accepted by ACL 2026 Findings
profile photo Efficient Agent Training for Computer Use
Yanheng He*, Jiahe Jin*, Pengfei Liu
Accepted by ICLR 2026
profile photo Deep research comparator: A platform for fine-grained human annotations of deep research agents
Prahaladh Chandrahasan*, Jiahe Jin*, Zhihan Zhang*, Tevin Wang, Andy Tang, Lucy Mo, Morteza Ziyadi, Leonardo FR Ribeiro, Zimeng Qiu, Markus Dreyer, Akari Asai, Chenyan Xiong
Accepted by WWW demo 2026
profile photo Revisiting 3D LLM Benchmarks: Are We Really Testing 3D Capabilities?
Jiahe Jin*, Yanheng He*, Mingyan Yang*
Accepted by ACL 2025 Findings
profile photo PCAgent: While You Sleep, AI Works - A Cognitive Journey into Digital World
Yanheng He*, Jiahe Jin*, Shijie Xia, Jiadi Su, Runze Fan, Haoyang Zou, Xiangkun Hu, Pengfei Liu
Preprint

Credits to Jon Barron for the website design.