Zhiyuan Li
2 indexed papers
Recent (6 mo)
2With code
0Influential cites
0Benchmarked
0Publications per year
226
Top categories
AI×2ML×1Crypto×1
Frequent co-authors
Research Timeline
2026
Towards Secure Agent Skills: Architecture, Threat Taxonomy, and Security Analysis
This paper provides the first comprehensive security analysis of the Agent Skills framework, identifying severe structural vulnerabilities that require fundamental architectural changes rather than simple mitigations.
When Does Persona Prompting Actually Help? A Retrieval and Metric Analysis of Expert Role Injection in LLMs
Persona prompting does not universally improve LLM performance; instead, it systematically trades increased expertise depth for reduced clarity, making multi-metric evaluation essential.
Highlighted terms show continued research focus across papers
Papers
cs.AIcs.LGRecentMay 28, 2026
When Does Persona Prompting Actually Help? A Retrieval and Metric Analysis of Expert Role Injection in LLMs
Shuai Xiao, Su Liu, Weikai Zhou, Jialun Wu +3 more
Persona prompting does not universally improve LLM performance; instead, it systematically trades increased expertise depth for reduced clarity, making multi-metric evaluation essential.
View →
cs.CRcs.AIRecentApr 3, 2026