牛哥精选 · 半年

📋 全部 🤖 AI·大模型 ⚡ 效率工具 📝 深度技术 🚀 产品观察 💰 商业科技 🔓 开源项目 🎨 设计创意 📖 阅读推荐 🏷 资源合集 🌱 成长效率

🤖 AI·大模型 arXiv NLP 2026-06-04

Listening to the Workforce: Measuring Construction Worker Safety Attitudes from Social Media Discourse Using LLMs

用LLMs从社交媒体分析建筑工人安全态度，实现大规模精准测量，填补行业空白。

arXiv:2606.04450v1 Announce Type: new Abstract: Worker safety attitudes are key determinants of whether protective practices are applied or bypassed o…

大语言模型建筑安全社交媒体分析工人态度安全测量

🤖 AI·大模型 arXiv AI 2026-06-02

When Safe Skills Collide: Measuring Compositional Risk in Agent Skill Ecosystems

社区贡献的AI技能单独安全，组合却可能引发风险？本文提出SkillReact量化测评这一新安全问题

arXiv:2606.00448v1 Announce Type: cross Abstract: LLM agents increasingly rely on community-contributed skills that expand an agent's operational capa…

llm智能体 ai安全技能组合组合风险 skillreact

📅 日期

2026-05-20 2026-05-19

🐂 牛哥精选

Listening to the Workforce: Measuring Construction Worker Safety Attitudes from Social Media Discourse Using LLMs

When Safe Skills Collide: Measuring Compositional Risk in Agent Skill Ecosystems

📅 日期