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

Junyi Li

5 indexed papers

Recent (6 mo)
4
With code
0
Influential cites
0
Benchmarked
0

Publications per year

5
26

Top categories

NLP×5AI×3ML×3Crypto×1

Frequent co-authors

Zhengyang Tang3×
Xin Lai3×
Pengyuan Lyu3×
Yiduo Guo3×
Benyou Wang3×
Chengquan Zhang3×

Research Timeline

2026
Do Phone-Use Agents Respect Your Privacy?

The paper introduces MyPhoneBench, a new framework that demonstrates that current phone-use agents often fail to respect user privacy, even when successfully completing simple tasks, primarily due to unnecessary data disclosure.

PhoneWorld: Scaling Phone-Use Agent Environments

The paper introduces PhoneWorld, a scalable pipeline that automatically converts real-world GUI trajectories and screenshots into controllable, reproducible phone-use environments, significantly improving agent performance across multiple mobile benchmarks.

PhoneWorld: Scaling Phone-Use Agent Environments

The paper introduces PhoneWorld, a scalable pipeline that automatically converts real-world GUI trajectories and screenshots into controllable, reproducible phone-use environments, significantly improving agent performance across multiple mobile benchmarks.

SkillHarm: Lifecycle-Aware Skill-Based Attacks via Automated Construction

The paper introduces SkillHarm, a comprehensive benchmark and automated framework for evaluating skill-based attacks across the entire agent skill-use lifecycle, demonstrating that current agents remain highly vulnerable to both fixed-payload and self-mutating poisoning attacks.

SkillHarm: Lifecycle-Aware Skill-Based Attacks via Automated Construction

The paper introduces SkillHarm, a comprehensive benchmark and automated framework for evaluating skill-based attacks across the entire agent skill-use lifecycle, demonstrating that current agents remain highly vulnerable to both fixed-payload and self-mutating poisoning attacks.

Highlighted terms show continued research focus across papers

Papers

cs.CLRecentJun 1, 2026

SkillHarm: Lifecycle-Aware Skill-Based Attacks via Automated Construction

Yuting Ning, Zhehao Zhang, Yash Kumar Lal, Boyu Gou +7 more

The paper introduces SkillHarm, a comprehensive benchmark and automated framework for evaluating skill-based attacks across the entire agent skill-use lifecycle, demonstrating that current agents rema…

View →
cs.CLRecentJun 1, 2026

SkillHarm: Lifecycle-Aware Skill-Based Attacks via Automated Construction

Yuting Ning, Zhehao Zhang, Yash Kumar Lal, Boyu Gou +7 more

The paper introduces SkillHarm, a comprehensive benchmark and automated framework for evaluating skill-based attacks across the entire agent skill-use lifecycle, demonstrating that current agents rema…

View →
cs.CLcs.AIcs.LGRecentMay 28, 2026

PhoneWorld: Scaling Phone-Use Agent Environments

Zhengyang Tang, Yuxuan Liu, Xin Lai, Junyi Li +20 more

The paper introduces PhoneWorld, a scalable pipeline that automatically converts real-world GUI trajectories and screenshots into controllable, reproducible phone-use environments, significantly impro…

View →
cs.CLcs.AIcs.LGRecentMay 28, 2026

PhoneWorld: Scaling Phone-Use Agent Environments

Zhengyang Tang, Yuxuan Liu, Xin Lai, Junyi Li +20 more

The paper introduces PhoneWorld, a scalable pipeline that automatically converts real-world GUI trajectories and screenshots into controllable, reproducible phone-use environments, significantly impro…

View →
cs.CRcs.AIcs.CLApr 1, 2026

Do Phone-Use Agents Respect Your Privacy?

Zhengyang Tang, Ke Ji, Xidong Wang, Zihan Ye +18 more

The paper introduces MyPhoneBench, a new framework that demonstrates that current phone-use agents often fail to respect user privacy, even when successfully completing simple tasks, primarily due to…

View →