Agentic Plan Caching: Test-Time Memory for Fast and Cost-Efficient LLM Agents
Qizheng Zhang, Michael Wornow, Gerry Wan, Kunle Olukotun
Conference on Neural Information Processing Systems (NeurIPS), 2025
Gerry Wan
I work on Gemini inference efficiency at Google.
I received my PhD in Computer Science from Stanford University, advised by Zakir Durumeric. Previously, I graduated summa cum laude with a BSE in Electrical Engineering from Princeton University, advised by Prateek Mittal.
[Email: gerryw at cs dot stanford dot edu]