Yiming Xiong

I am Yiming Xiong (熊一鸣), a Data Science Master's student at the University of British Columbia. My research interest lies in exploring self-improving agentic systems, with a focus on two directions: (1) how to leverage and improve LLMs' ability as a mutator to facilitate robust, reliable open-ended evolution processes and broader self-improving loops; (2) frontier exploration of what such processes can actually produce — currently focused on coding agentic systems.

I'm fortunate to work with Shengran Hu and Jeff Clune on self-improving agents, and to have collaborated with Youliang Yuan and Pinjia He during my undergraduate on AI safety and robustness.

Selected Research Program

Learning to Continually Learn via Meta-learning Agentic Memory Designs

Yiming Xiong, Shengran Hu, Jeff Clune

🏆 Best Paper @ MemAgents Workshop · Outstanding Paper @ RSI Workshop, ICLR 2026

Publications

Yiming Xiong, Shengran Hu, Jeff Clune. Learning to Continually Learn via Meta-learning Agentic Memory Designs. arXiv:2602.07755, 2026. arXiv

Youliang Yuan, Wenxuan Wang, Qingshuo Guo, Yiming Xiong, Chihao Shen, Pinjia He. Does ChatGPT Know That It Does Not Know? Evaluating the Black-Box Calibration of ChatGPT. LREC-COLING 2024, pp. 5191–5201. ACL Anthology