AI safety researcher

Xiaogang Xu

Zhejiang Normal University

Google Scholar dblp ORCID

Last 12 months3 papers

Evaluation and benchmarks 1

AI safety papers from the last year

On this site: 13 papers

May 2026

LITMUS: Benchmarking Behavioral Jailbreaks of LLM Agents in Real OS Environments
May 11Evaluation and benchmarksarXiv ↗

April 2026

ACIArena: Toward Unified Evaluation for Agent Cascading Injection
Apr 9arXiv ↗

March 2026

From Thinker to Society: Security in Hierarchical Autonomy Evolution of AI Agents
Mar 8arXiv ↗

Authorship follows dblp and the author's own Google Scholar profile; only AI safety papers on this site are listed.