TARS: A Theory-of-Mind Agent for Personalized In-IDE Code Comprehension

  • 类型:arxiv
  • 标识:2607.15948
  • 链接:http://arxiv.org/abs/2607.15948v1
  • 主分类:agent
  • 形态:method
  • 被引:0
  • 被引来源:Semantic Scholar
  • S2被引:0
  • 影响力被引:0
  • TLDR:TARS is an LLM-powered agent integrated into Visual Studio Code that supports program comprehension through autonomous explanations anchored directly to the code under analysis, built around a lightweight Theory of Mind paradigm.
  • 待LLM分类:否
  • 标题中文:TARS:用于IDE内个性化代码理解的Theory-of-Mind Agent
  • TLDR中文:TARS是一个集成在Visual Studio Code中的LLM驱动Agent,通过直接锚定到被分析代码的自主解释来支持程序理解,基于轻量级心智理论范式构建。
  • 来源文件
  • /inbox/tom/_candidates/2026-07-20-agent-rag-longcontext-candidates.json
  • [S2 enrich]