Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Xiaogang Xu

Xiaogang Xu

3 indexed papers

Recent (6 mo)
3
With code
0
Influential cites
0
Benchmarked
0

Publications per year

3
26

Top categories

NLP×3AI×2Crypto×2Multiagent×1

Frequent co-authors

Zhen Yang1×
Wen Wang1×
Cong Chen1×
Xander Xu1×
Ying-Cong Chen1×
Chiyu Zhang1×

Research Timeline

2026
ACIArena: Toward Unified Evaluation for Agent Cascading Injection

The paper introduces ACIArena, a unified and comprehensive evaluation framework designed to systematically test the robustness of Multi-Agent Systems against complex Agent Cascading Injection attacks.

LITMUS: Benchmarking Behavioral Jailbreaks of LLM Agents in Real OS Environments

The paper introduces LITMUS, a novel benchmark that rigorously tests LLM agents for dangerous, physical-layer behavioral jailbreaks in real OS environments, revealing that current agents frequently execute high-risk operations despite safety guardrails.

Streaming Communication in Multi-Agent Reasoning

The paper introduces StreamMA, a streaming multi-agent reasoning system that significantly reduces latency and improves effectiveness by passing reasoning steps to downstream agents as they are generated, rather than waiting for the entire chain to complete.

Highlighted terms show continued research focus across papers

Papers

cs.CLcs.AIcs.MARecentJun 3, 2026

Streaming Communication in Multi-Agent Reasoning

Zhen Yang, Xiaogang Xu, Wen Wang, Cong Chen +2 more

The paper introduces StreamMA, a streaming multi-agent reasoning system that significantly reduces latency and improves effectiveness by passing reasoning steps to downstream agents as they are genera…

View →
cs.CRcs.CLRecentMay 11, 2026

LITMUS: Benchmarking Behavioral Jailbreaks of LLM Agents in Real OS Environments

Chiyu Zhang, Huiqin Yang, Bendong Jiang, Xiaolei Zhang +7 more

The paper introduces LITMUS, a novel benchmark that rigorously tests LLM agents for dangerous, physical-layer behavioral jailbreaks in real OS environments, revealing that current agents frequently ex…

View →
cs.AIcs.CLcs.CRRecentApr 9, 2026

ACIArena: Toward Unified Evaluation for Agent Cascading Injection

Hengyu An, Minxi Li, Jinghuai Zhang, Naen Xu +5 more

The paper introduces ACIArena, a unified and comprehensive evaluation framework designed to systematically test the robustness of Multi-Agent Systems against complex Agent Cascading Injection attacks.

View →