Sun, Jiayang

OSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks

Yuan, M., Zhou, Z., Xiong, X., Wu, W., Sun, J., Song, J., Cui, K., Wang, B., Wu, H., Li, Y., et al. (2026) · arXiv

AI-based Problem Solving and PlanningArtificial Intelligence Applications

Cited by 79

Proof-or-Stop: Don't Trust the Agent, Trust the Evidence -- Loop Engineering for Verifiable Evidence-Gated Lifecycle Control

Huang, J., Hsia, J., Sun, J., Shi, F., Huang, W., & White, I. H. (2026) · arXiv

Software Engineering Techniques and PracticesSoftware Engineering Research

Cited by 0