Author

Yu-Sai Zhao

h-index 1 View on Semantic Scholar

We have 2 of 3 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Jul 2026

OmegaUse-OfficeVal: Benchmarking LLM Agents on Long-Horizon Office-Suite Tasks with Economic Grounding

OmegaUse-OfficeVal is introduced, a benchmark for evaluating LLM agents on long-horizon office-suite tasks with task-level economic grounding, and code-based verifiers from fine-grained rubrics are developed to support stable evaluation.

Jing-Bo Zhou, Yu-Sai Zhao, Qi Bao et al. · arXiv.org · 1 citation

#artificial intelligence Preprint Open access Sep 2026

OmegaUse-SOP: SOP Engineering for Professional Computer Use from Human Demonstrations

OmegaUse-SOP is introduced, a human-in-the-loop SOP Engineering system for transforming human demonstrations of professional computer use into reusable SOP skills for GUI agents, and the results suggest that OmegaUse-SOP can improve GUI-agent reliability on professional SOP tasks.

Yixiong Xiao, L. An, Hu-Cheng Yang et al. · 0 citations