Amir Moeini

Hi! I'm a Ph.D. student at University of Virginia advised by Shangtong Zhang, and a member of the Sequential Intelligence Lab. Before UVA, I earned my B.S. in Computer Engineering from Sharif University of Technology. My research lies in the intersection of reinforcement learning, in-context learning, and large language models.

Email | Google Scholar | Github

Publications

Latent Q-Barrier Shielding for Safe In-Context Reinforcement Learning

Kwon M.*, Moeini A.*, Zhang S., Feng L.
Preprint
paper

MathlibLemma: Folklore Lemma Generation and Benchmark for Formal Mathematics

Liu X., Xie Z., Moeini A., Chen C., Liu S.D., Meng Y., Zhang A., Zhang S.
ICML 2026
paper

Safe In-Context Reinforcement Learning

Moeini A.*, Kwon M.*, Bozkurt A.K., Motai Y., Chandra R., Feng L., Zhang S.
ICML 2026
paper | code

Reward Is Enough: LLMs Are In-Context Reinforcement Learners

Song K.*, Moeini A.*, Wang P., Gong L., Chandra R., Qi Y., Zhang S.
ICLR 2026
paper

A Survey of In-Context Reinforcement Learning

Moeini A., Wang J., Beck J., Blaser E., Whiteson S., Chandra R., Zhang S.
Preprint
paper | thread

Mathador-LM: A Dynamic Benchmark for Mathematical Reasoning on Large Language Models

Kurtic E.*, Moeini A.*, Alistarh D.
EMNLP 2024
paper | code | thread

Education

University of Virginia (Sep 2024 - Present)

Ph.D. student in Computer Science

University of Virginia (Sep 2024 - Jan 2026)

M.S. in Computer Science

Sharif University of Technology (Sep 2018 - Mar 2024)

B.S. in Computer Engineering

Last updated: May 2026 Template