Jerry Huang

I am a master's student at the University of Illinois Urbana-Champaign (UIUC) advised by Professor Tong Zhang. I obtained my BS in computer science in 2022 from Duke University.

In the past, I have been at:

  1. Research: NewsBreak – LLM- and Agent-based reasoning and retrieval.
  2. Finance: Optiver and Old Mission Capital – Quantitative trading.
  3. Software: VectorShift – Founding engineer; Secureframe and Amazon – Software engineering intern; Vertex Protocol – Smart contract developer.

I am interested in continual learning, curriculum learning, and memory structures, and how they may be used to improve the performance of language models and multi-agent systems.

You can reach me at jerry8@illinois.edu.

Google Scholar / LinkedIn

Jerry Huang profile photo
project image

RAG-RL: Advancing Retrieval-Augmented Generation via RL and Curriculum Learning


Jerry Huang, Siddarth Madala, Risham Sidhu, Cheng Niu, Hao Peng, Julia Hockenmaier, Tong Zhang
arXiv, 2025
arxiv /

We introduce RAG-RL, an answer generation model trained to identify and reason over larger sets of retrieved information using reinforcement learning and curriculum learning.




Design and source code from Jon Barron's website