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

Peng Xu

3 indexed papers

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

Publications per year

3
26

Top categories

AI×3Crypto×2

Frequent co-authors

Hongxiang Lin1×
Zhirui Kuai1×
Erpeng Xue1×
Lei Wang1×
Qi Li1×
Jiu Li1×

Research Timeline

2026
Temporal UI State Inconsistency in Desktop GUI Agents: Formalizing and Defending Against TOCTOU Attacks on Computer-Use Agents

The paper formalizes TOCTOU vulnerabilities in GUI agents due to observation-to-action delays and proposes a layered defense, Pre-execution UI State Verification (PUSV), achieving high interception rates against various attacks.

A Comparative Evaluation of AI Agent Security Guardrails

This paper comparatively evaluates DKnownAI Guard against three competitors, demonstrating that DKnownAI Guard achieves superior performance in detecting both agent-specific threats and harmful content.

SKILLC: Learning Autonomous Skill Internalization in LLM Agents via Contrastive Credit Assignment

SkillC introduces a Contrastive Skill Credit Assignment (CSCA) framework to enable LLM agents to autonomously internalize skills during training, significantly outperforming existing methods without requiring runtime skill access.

Highlighted terms show continued research focus across papers

Papers

cs.AIRecentMay 27, 2026

SKILLC: Learning Autonomous Skill Internalization in LLM Agents via Contrastive Credit Assignment

Hongxiang Lin, Zhirui Kuai, Erpeng Xue, Lei Wang

SkillC introduces a Contrastive Skill Credit Assignment (CSCA) framework to enable LLM agents to autonomously internalize skills during training, significantly outperforming existing methods without r…

View →
cs.CRcs.AIRecentApr 27, 2026

A Comparative Evaluation of AI Agent Security Guardrails

Qi Li, Jiu Li, Pingtao Wei, Jianjun Xu +7 more

This paper comparatively evaluates DKnownAI Guard against three competitors, demonstrating that DKnownAI Guard achieves superior performance in detecting both agent-specific threats and harmful conten…

View →
cs.CRcs.AIRecentApr 20, 2026

Temporal UI State Inconsistency in Desktop GUI Agents: Formalizing and Defending Against TOCTOU Attacks on Computer-Use Agents

Wenpeng Xu

The paper formalizes TOCTOU vulnerabilities in GUI agents due to observation-to-action delays and proposes a layered defense, Pre-execution UI State Verification (PUSV), achieving high interception ra…

View →