OpenSkillEval: Automatically Auditing the Open Skill Ecosystem for LLM Agents 事件

OpenSkillEval: Automatically Auditing the Open Skill Ecosystem for LLM Agents arXiv:2605.23657v2 Announce Type: replace Abstract: Skills, i.e., structured workflow instructions distilled for large language models (LLMs), are becoming an increasingly important mechanism for improving agent performance on real-world downstream tasks. However, as the open-source skill ecosystem rapidly expands, it remains unclear how different models and agent frameworks interact with skills, how to evaluate skill