讀紙 ReadPaper

由 Claude Code Max 翻譯的 AI 論文繁體中文版 · 101 篇

篩選標籤: Interpretability 2 篇 × 清除
2608.10218v1 arXiv License Anthropic

心智病毒:多代理 LLM 系統中會自我傳播的想法

Mind Viruses: Self-Propagating Ideas in Multi-Agent LLM Systems

Vassilis Papadopoulos、McNair Shah、Sam Zimmerman、Jack Lindsey(Anthropic Fellows Program、Anthropic、EPF...

AI SafetyMulti-Agent SystemsLLM AgentsMind VirusPrompt InjectionEmergent BehaviorInterpretability紅隊測試
Liang-Hsun Huang 許願
2605.14038v2 CC BY 4.0 Meta

模型自適應的工具必要性揭示了 LLM 工具使用中的「知行落差」

Model-Adaptive Tool Necessity Reveals the Knowing-Doing Gap in LLM Tool Use

Yize Cheng, Chenrui Fan, Mahdi JafariRaviz, Keivan Rezaei, Soheil Feizi(University of Maryland, Coll...

LLMTool UseAgentProbingMeta-cognitionInterpretability知行落差
Teds Lin 許願