Siqi Yang 杨思琪

01About

I'm Siqi Yang, currently pursuing my MSCS (research track) at the University of Illinois Urbana‑Champaign, where I am fortunate to be advised by Prof. Yu‑Xiong Wang.

My research centers on coding agents and self-evolving AI systems: how the harness around a model — its prompts, tools, memory, and workflow — can be designed, evolved, and analyzed, and what such an evolved artifact actually encodes. My work spans agent harness design, reinforcement learning, and LLM post-training.

In summer 2026 I was a research intern at IBM Research in Yorktown Heights, where I built an instrumented self-evolving coding-agent harness and studied how its gains split between language-specific and model-specific compensation.

Before joining UIUC, I completed my B.Eng in Electronic Engineering at Tsinghua University, where I worked with Prof. Huazhe Xu and Prof. Yu Wang on robot learning and imitation learning.

02Selected Publications

04Education

05Honors & Service

07Contact

I'm always happy to hear from people working on agents, RL, or LLM post-training. The fastest way to reach me is email.