Jiatong Li

I am a first-year Ph.D. student in the School of Computer, Data & Information Sciences at University of Wisconsin-Madison where I am fortunate to be advised by Dr. Sharon Li. My current research focuses on Agentic Memory for LLM Agents and User-Engaged LLM agents.

Previously, I earned my M.S. and B.S. degrees in Data Science from University of Science and Technology of China (USTC) in 2025 and 2022, respectively, under the supervision of Dr. Qi Liu. My prior research experience spans perturbation-driven LLM robustness evaluation, data mining, and cognitive diagnosis for intelligent education. Throughout my academic journey, I have had the pleasure of collaborating with Dr. Mengxiao Zhu at USTC, Dr. Xiang Liu at Educational Testing Service, Dr. Renjun Hu at Alibaba Cloud, and Dr. Yifei Yuan at University of Copenhagen.

News

Jan 27, 2026	Our Adaptive ELO and Test-time Correction of Reasoning are accepted by ICLR 2026
Nov 07, 2025	Our Cognitive Adaptive Selection Strategy is accepted by AAAI 2026
Sep 18, 2025	Our Vittle, is accepted by NeurIPS 2025
May 01, 2025	Our recent research about trustworthy evaluation, am-ELO, is accepted by ICML 2025 (Spotlight)
Oct 15, 2024	Check out our Awesome LM Evaluation Methodologies, a collection of frontier papers in LM Eval Methodologies
Sep 27, 2024	PertEval and CCAT are accepted by NeurIPS 2024. PertEval is selected as a Spotlight
May 30, 2024	Complete my research intern at Alibaba Cloud. Many thanks to my mentor and all collaborators!
May 30, 2024	PertEval is available at Arxiv. [Paper]
Jan 23, 2024	ID-CDF is accepted by TheWebConf 2024. [Paper]
Jan 06, 2024	Start my research intern in LLM evaluation at Alibaba Cloud
Sep 18, 2023	DeepEval is available at Arxiv. [Paper]
Mar 18, 2023	One research about Bayesian Item Response Theory is invited to make an oral presentation at IMPS 2023, University of Maryland, College Park, USA. [Web]
May 20, 2022	HierCDF is accepted by SIGKDD 2022. [Paper]