Chuxuan Hu

About Me

Hi! I am a 3rd-year CS Ph.D. candidate at the University of Illinois at Urbana-Champaign (UIUC), advised by Prof. Daniel Kang. My research focuses on AI agents and LLM post-training for data.

Selected Publications — full list on Google Scholar

Preprint

SODIUM: From Open Web Data to Queryable Databases

Chuxuan Hu, Philip Li, Maxwell Yang, and Daniel Kang

Preprint, 2026

paper code

ICLR 2026

Breaking Barriers: Do Reinforcement Post Training Gains Transfer To Unseen Domains?

Chuxuan Hu, Yuxuan Zhu, Antony Kellermann, Caleb Biddulph, Suppakit Waiwitlikhit, Jason Benn, and Daniel Kang

International Conference on Learning Representations (ICLR), 2026

paper code data

SIGMOD 2026

DRAMA: Unifying Data Retrieval and Analysis for Open-Domain Analytic Queries

Chuxuan Hu, Maxwell Yang, James Weiland, Yeji Lim, Suhas Palawala, and Daniel Kang

ACM International Conference on Management of Data (SIGMOD), 2026

paper code

ACL 2025

REPRO-Bench: Can AI Agents Assess the Reproducibility of Social Science Papers?

Chuxuan Hu, Liyun Zhang, Yeji Lim, Aum Wadhwani, Austin Peters, and Daniel Kang

Findings of the Association for Computational Linguistics (ACL), 2025

paper data code

VLDB 2025

LEAP: LLM-powered End-to-end Automatic Library for Processing Social Science Queries on Unstructured Data

Chuxuan Hu, Austin Peters, and Daniel Kang

Proceedings of the VLDB Endowment, 2025

paper code data

SDM 2024

GENIUS: Subteam Replacement with Clustering-based Graph Neural Network

Chuxuan Hu, Qinghai Zhou, and Hanghang Tong

SIAM International Conference on Data Mining (SDM), 2024

paper code

Industry Experience

Microsoft Research · Research Intern · Redmond, WA

May – Aug 2025

Hosted by Dr. Yeye He, Data Systems Group

Teaching Experience

Fall 2025

Teaching Assistant — CS 411: Database Systems