About
Hi, I'm Shibo (Robin) Jin, a PhD student in Computer and Information Science at the University of Pennsylvania, advised by Prof. Mayur Naik. Before starting my PhD, I earned an MSE in the same field at Penn and a BASc in Computer Engineering from the University of British Columbia.
My research interests center on LLM agents and multi-agent systems, especially agent self-improvement and co-evolution. I am interested in how agents can generate useful challenges and feedback for themselves and one another, and how these interactions might support recursive self-improvement over time.
Feel free to email me if you'd like to discuss related research or explore a collaboration.
News
Started my PhD in Computer and Information Science at the University of Pennsylvania.
MathDuels was accepted to COLM 2026.
Publications
* indicates equal contribution.

Environment Duels: A Microcosm of LLM Co-Evolution
Shibo Jin*, Zhiqiu Xu*, Yiling Zou, Shangyu Gong, Mayur Naik
Manuscript under review 2026

MathDuels: A Self-Play Benchmark That Grows
Zhiqiu Xu*, Shibo Jin*, Shreya Arya, Mayur Naik
Conference on Language Modeling (COLM) 2026

Next-Scale Autoregressive Models for Text-to-Motion Generation
Zhiwei Zheng, Shibo Jin, Lingjie Liu, Mingmin Zhao
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2026
