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

Shuo Chen

4 indexed papers

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

Publications per year

4
26

Top categories

AI×3Crypto×2Prog. Lang.×1

Frequent co-authors

Liuji Chen1×
Dianxing Tang1×
Xing Shi1×
Dingshuo Chen1×
Qiang Liu1×
Shu Wu1×

Research Timeline

2026
PAuth - Precise Task-Scoped Authorization For Agents

The paper introduces PAuth, a new authorization model that grants agents only the precise permissions needed for a specific natural-language task, preventing overprivileging inherent in existing operator-scoped models.

Evolving Skill-Structured Attack Memory Enhances LLM Jailbreaking

The paper proposes MemoAttack, a memory-driven black-box jailbreak framework that systematically models, evolves, and selects attack experiences to significantly enhance LLM jailbreaking success rates.

AnyEdit++: Adaptive Long-Form Knowledge Editing via Bayesian Surprise

AnyEdit++ introduces a structure-aware framework that uses Bayesian Surprise to adaptively segment long-form knowledge, significantly improving the coherence and accuracy of knowledge editing in LLMs.

Learning When Not to Act: Mitigating Tool Abuse in Agentic Reinforcement Learning

The paper proposes EAPO, a framework that enables agentic models to learn when to forgo using external tools, thereby mitigating tool abuse while maintaining high reasoning accuracy.

Highlighted terms show continued research focus across papers

Papers

cs.AIRecentJun 1, 2026

Learning When Not to Act: Mitigating Tool Abuse in Agentic Reinforcement Learning

Liuji Chen, Dianxing Tang, Xing Shi, Dingshuo Chen +3 more

The paper proposes EAPO, a framework that enables agentic models to learn when to forgo using external tools, thereby mitigating tool abuse while maintaining high reasoning accuracy.

View →
cs.AIRecentMay 31, 2026

AnyEdit++: Adaptive Long-Form Knowledge Editing via Bayesian Surprise

Bowen Tian, Caixue He, Jiemin Wu, Jingying Wang +3 more

AnyEdit++ introduces a structure-aware framework that uses Bayesian Surprise to adaptively segment long-form knowledge, significantly improving the coherence and accuracy of knowledge editing in LLMs.

View →
cs.CRRecentMay 28, 2026

Evolving Skill-Structured Attack Memory Enhances LLM Jailbreaking

Junke Zhang, Jianwei Wang, Sishuo Chen, Yizhang He +2 more

The paper proposes MemoAttack, a memory-driven black-box jailbreak framework that systematically models, evolves, and selects attack experiences to significantly enhance LLM jailbreaking success rates…

View →
cs.CRcs.AIcs.PLRecentMar 17, 2026

PAuth - Precise Task-Scoped Authorization For Agents

Reshabh K Sharma, Linxi Jiang, Zhiqiang Lin, Shuo Chen

The paper introduces PAuth, a new authorization model that grants agents only the precise permissions needed for a specific natural-language task, preventing overprivileging inherent in existing opera…

View →