Yurun Chen

About Me

Hi! I'm Yurun Chen, a Ph.D. student at Zhejiang University, advised by Shengyu Zhang and Keting Yin.

I work on the safety of Computer-Using Agents (CUAs). My research centers on two complementary questions: how to equip CUAs with effective guardrails for robust task execution under real-world noise and uncertainty, and how to systematically develop red-teaming strategies that uncover safety vulnerabilities in realistic deployment settings.

Open to collaborations on CUA red-teaming, safety, guardrails, and evaluation. Reach out via email.

Research Directions

• CUA guardrails (HarmonyGuard, SafePred): Predictive safety layers for GUI agents. Block or steer risky actions before they run, while keeping the agent useful under noisy or ambiguous interfaces.
• Red-teaming and robustness (AEIA): Test multimodal agents against attacks injected through the environment, such as manipulated page content or UI context.
• Agent evaluation (Graph2Eval): Build benchmarks and scoring methods for long-horizon GUI tasks, including automatic task generation and process-level rewards.