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

Na Zou

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

Mingxuan Zhang2×
Jiahui Han2×
Dadi Guo2×
Songze Li2×
Guanchu Wang2×
Dongrui Liu2×

Research Timeline

2026
SkillsInjector: Dynamic Skill Context Construction for LLM Agents

SkillsInjector proposes a two-stage adaptive method to dynamically optimize skill selection, quantity, and presentation for LLM agents, significantly improving task performance over static injection methods.

PrivacyPeek: Auditing What LLM-Based Agents Acquire, Not Just What They Say

The paper introduces PrivacyPeek, a new benchmark that audits the acquisition stage of LLM-based agents to show that unnecessary and sensitive data acquisition is a widespread and critical privacy vulnerability.

PrivacyPeek: Auditing What LLM-Based Agents Acquire, Not Just What They Say

The paper introduces PrivacyPeek, a new benchmark that audits the acquisition stage of LLM-based agents to demonstrate that unnecessary acquisition of sensitive data is a widespread and critical privacy vulnerability.

Highlighted terms show continued research focus across papers

Papers

cs.CRcs.AIRecentMay 29, 2026

PrivacyPeek: Auditing What LLM-Based Agents Acquire, Not Just What They Say

Mingxuan Zhang, Jiahui Han, Dadi Guo, Songze Li +4 more

The paper introduces PrivacyPeek, a new benchmark that audits the acquisition stage of LLM-based agents to show that unnecessary and sensitive data acquisition is a widespread and critical privacy vul…

View →
cs.CRcs.AIRecentMay 29, 2026

PrivacyPeek: Auditing What LLM-Based Agents Acquire, Not Just What They Say

Mingxuan Zhang, Jiahui Han, Dadi Guo, Songze Li +4 more

The paper introduces PrivacyPeek, a new benchmark that audits the acquisition stage of LLM-based agents to demonstrate that unnecessary acquisition of sensitive data is a widespread and critical priva…

View →
cs.AIRecentMay 28, 2026

SkillsInjector: Dynamic Skill Context Construction for LLM Agents

Yanchao Li, Wanhao Liu, Ben Gao, Jiaqing Xie +4 more

SkillsInjector proposes a two-stage adaptive method to dynamically optimize skill selection, quantity, and presentation for LLM agents, significantly improving task performance over static injection m…

View →