KUPAS MASTER: Distilling the Tacit Expertise of Master Practitioners into Agent-Ready Experience Corpora

  • 类型：arxiv
  • 标识：2609.37673
  • 链接：http://arxiv.org/abs/2609.37673v1
  • 主分类：agent
  • 形态：method
  • TLDR：Experienced professionals know more than just facts and conclusions. They know which cues matter, why a judgment is reasonable, and which action to take. Routine work records often leave out this tacit knowledge, making it difficult for Large Language Model (LLM) agents to use professional experience effectively. We introduce KUPAS MASTER, an experience engineering platform built around nine-layer cognitive corpus construction. It turns heterogeneous work records and practitioner interviews into traceable, reusable experience corpora for agents. Six case elements preserve the task process: con
  • 待LLM分类：否
  • 标题中文：[标题中文] KUPAS MASTER：将资深从业者的隐性专业知识蒸馏为 Agent 可用的经验语料
  • TLDR中文：[TLDR中文] 经验丰富的专业人士所掌握的远不止事实与结论。他们知道哪些线索是关键、为什么某个判断是合理的，以及应当采取哪种行动。日常工作记录往往省略了这些隐性知识，使得 LLM Agent 难以有效利用专业经验。我们提出 KUPAS MASTER，一个围绕九层认知语料构建的经验工程平台，可将异构的工作记录与从业者访谈转化为 Agent 可追溯、可复用的经验语料。六个案例要素保留任务过程
  • 来源文件：
  • /inbox/tom/_candidates/2026-09-30-agent-rag-longcontext-candidates.json