Author

Yimin Liu

Observed name: Liu, Yimin

Institutions: University of Southern California, The Ohio State University

Observed institutions: University of Southern California, The Ohio State University

OpenAlex ID: A5133209021

SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks

2026 · Li, Xiangyi, Liu, Yimin, et al. · arXiv (Cornell University) · 3

What Happens During Autonomous Deep Research After the User Steps Away?

2026 · Liu, Yimin, Zhang, Yijia, et al. · arXiv (Cornell University)

BenchShield: Formal Model-Backed Instrumentation for Reward Integrity in LLM-Agent Evaluation Infrastructure

2026 · Zheng, Shenghan, Di, Zonglin, et al. · arXiv (Cornell University)

SkillsMetric: Mapping the Detection Boundary of Static Analysis for Malicious Agent Skills

2026 · Chen, Xinze, Zhang, Chi, et al. · arXiv (Cornell University)

What Keeps Agent Skills from Being Reusable? Evidence from 138K SKILL.md Files

2026 · Zhang, Chi, Liu, Yimin, et al. · arXiv (Cornell University)

ClawsBench: Evaluating Capability and Safety of LLM Productivity Agents in Simulated Workspaces

2026 · Li, Xiangyi, Choe, Kyoung Whan, et al. · arXiv (Cornell University)

Works count: 6

Citation count: 3

H-index: 1

I10-index: