Chris Rawles

Chris Rawles

Staff Research Engineer · Google DeepMind

I work on LLM agents that operate computers. I'm currently on the Gemini Thinking & Reasoning team, focused on coding agents. Previously I led the AndroidWorld and Android in the Wild projects — large-scale benchmarks and datasets for computer use agents (CUAs).

Before moving to research, I worked in data science at Pivotal and applied engineering at Google. I hold an M.S. from UW–Madison and a B.A. from UC Berkeley.

Selected Publications

AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents

C. Rawles, S. Clinckemaillie, Y. Chang, J. Waltz, G. Lau, M. Fair, A. Li, W. Bishop, W. Li, F. Campbell-Ajala, et al.

ICLR 2025

On the Effects of Data Scale on UI Control Agents

W. Li, W. Bishop, A. Li, C. Rawles, F. Campbell-Ajala, D. Tyamagundlu, et al.

NeurIPS 2024

Latent State Estimation Helps UI Agents to Reason

W. Bishop, A. Li, C. Rawles, O. Riva

arXiv · 2024

Android in the Wild: A Large-Scale Dataset for Android Device Control

C. Rawles, A. Li, D. Rodriguez, O. Riva, T. Lillicrap

NeurIPS 2023