Papers2

All Beginner Intermediate Advanced

All Sources arXiv

#sandboxing

Agent Skills in the Wild: An Empirical Study of Security Vulnerabilities at Scale

Beginner

Yi Liu, Weizhe Wang et al.Jan 15arXiv

Agent skills are like apps for AI helpers, but many of them are not carefully checked for safety yet.

#agent skills#AI security#prompt injection

Let It Flow: Agentic Crafting on Rock and Roll, Building the ROME Model within an Open Agentic Learning Ecosystem

Intermediate

Weixun Wang, XiaoXiao Xu et al.Dec 31arXiv

This paper builds an open, end-to-end ecosystem (ALE) that lets AI agents plan, act, and fix their own mistakes across many steps in real computer environments.

#agentic LLMs#reinforcement learning#IPA