Skill VM: Write Once, Run Everywhere Efficiently
Le Chen, Erhu Feng, Yubin Xia, Haibo Chen
2026Year
Abstract
LLM agents increasingly adopt skills as a reusable unit of composition. While skills are shared across diverse agent platforms, current systems treat them as raw context, causing the same skill to behave inconsistently for different agents. This fragility undermines skill portability and execution efficiency.
Ask about this paper
Ask your agent about it.
Lune has read the top-tier papers around this one, so every answer names the papers it rests on.
Your agent calls
Lunesearch_papers
Free to start. No credit card required.
Terminal
Install the CLIlune papers get bf6c7b90-e466-4ad6-abf0-a9d788055114Related papers
- PragLocker: Protecting Agent Intellectual Property in Untrusted Deployments via Non-Portable PromptsQinfeng Li, Yuntai Bao, Jianghui Hu, Wenqi Zhang et al.ICML 2026
- PolySkill: Learning Generalizable Skills Through Polymorphic Abstraction For Continual LearningSimon Yu, Gang Li, Weiyan Shi, Peng QiICLR 2026 · 11 citations
- Efficient Skill Grounding via Code Refactoring with Small Language ModelsSera Choi, Wonje Choi, Saehun Chun, Daehee Lee et al.ICML 2026
- SkillScope: Toward Fine-Grained Least-Privilege Enforcement for Agent SkillsJiangrong Wu, Yuhong Nan, Yixi Lin, Huaijin Wang et al.CCS 2026 · 5 citations
- "Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the WildYi Liu, Zhihao Chen, Yanjun Zhang, Gelei Deng et al.USENIX Security 2026 · 46 citations
