2 papers
cs.CR2026
SkCC: Portable and Secure Skill Compilation for Cross-Framework LLM Agents
Yipeng Ouyang, Yi Xiao, Yuhao Gu +1
LLM agents increasingly rely on reusable skills (e.g., SKILL markdown files) to execute complex tasks, yet these artifacts lack portability: agent frameworks are highly sensitive t…
cs.SE2026
Benchmarks are Not Enough: RAMP for Runtime Assessing of Agentic Models in Production Systems
Yipeng Ouyang, Xin Huang, Bingjie Liu +3
LLM agents are rapidly evolving from coding assistants into autonomous software engineering systems. However, existing evaluation methodologies remain largely centered on static, i…