Shanyong Wang

Hi there👋 My name is Shanyong Wang. I am a junior undergraduate at ShanghaiTech University and an exchange student at UIUC in 2024, majoring in computer science. I am very fortunate to join UIUC BLENDER Lab, advised by Prof. Heng Ji and mentor Xiusi Chen. I also work closing with Prof. Ze Xiong at WiSe lab back in ShanghaiTech University.

My Chinese name is 王善泳. My pronouns are He/Him/His.

News
2025
We publish a paper named DecisionFlow, a novel decision modeling framework. And happliy end my exchange at UIUC.
May 19
2024
Begin my exchange at UIUC.
Aug 21
Education
  • ShanghaiTech University
    Sept. 2022 - Jun. 2026
    Bachelor of Computer Science
  • University of Illinois Urbana-Champaign(UIUC)
    Aug. 2024 - May. 2025
    Visiting Student
    Computer Sciences
Experience
logo
Rutgers University
Advised by Prof. Yongfeng Zhang.
Jun. 2025 - Present
Design for AIOS.
logo
University of Illinois Urbana-Champaign(UIUC)
Advised by Prof. Heng Ji and mentor Xiusi Chen.
Oct. 2024 - May. 2025
Design a novel decision modeling framework.
logo
ShanghaiTech Univeristy
Advised by Prof. Ze Xiong.
Designed, modeled, and coded various virtual environments.
Publications
DecisionFlow: Advancing Large Language Model as Principled Decision Maker
DecisionFlow: Advancing Large Language Model as Principled Decision Maker

Xiusi Chen*, Shanyong Wang*, Cheng Qian*, Hongru Wang*, Peixuan Han, Heng Ji (* equal contribution)

2025

We propose DecisionFlow, a novel decision modeling framework that guides models to reason over structured representations of actions, attributes, and constraints. Rather than predicting answers directly from prompts, DecisionFlow builds a semantically grounded decision space and infers a latent utility function to evaluate trade-offs in a transparent, utility-driven manner. This process produces decisions tightly coupled with interpretable rationales reflecting the model's reasoning.

DecisionFlow: Advancing Large Language Model as Principled Decision Maker

Xiusi Chen*, Shanyong Wang*, Cheng Qian*, Hongru Wang*, Peixuan Han, Heng Ji (* equal contribution)

2025

We propose DecisionFlow, a novel decision modeling framework that guides models to reason over structured representations of actions, attributes, and constraints. Rather than predicting answers directly from prompts, DecisionFlow builds a semantically grounded decision space and infers a latent utility function to evaluate trade-offs in a transparent, utility-driven manner. This process produces decisions tightly coupled with interpretable rationales reflecting the model's reasoning.

Selected Projects
About Me

I love playing basketball.