KUPAS MASTER: Distilling the Tacit Expertise of Master Practitioners into Agent-Ready Experience Corpora
作者: Changmian Wang, Yuchao Ma, Xuchao Lu, Chen Zhang, Ping Sun, Jiazheng Wang, Shan Wang, Xuanwen Chen, Yihe Sun, Ziyu Lu, Jianqiang Huang, Hongzhi Li, Ziqing Xia, Kaihua Tang, Xian-Sheng Hua, Qinghua Zheng
分类: cs.AI, cs.CL
发布日期: 2026-09-29
备注: Technical Report. Official website: https://lsf.kupasai.com/ Report homepage: https://tongjiai4e.github.io/KUPAS-MASTER-Report/
💡 一句话要点
提出KUPAS MASTER以解决专业知识转化为智能体经验的问题
🎯 匹配领域: 支柱二：RL算法与架构 (RL & Architecture) 支柱九：具身大模型 (Embodied Foundation Models)
关键词: 隐性知识 经验工程 认知语料库 智能体技术 知识管理 决策支持 多领域应用
📋 核心要点
- 现有方法往往无法有效捕捉和利用专业人士的隐性知识，导致智能体在实际应用中表现不佳。
- KUPAS MASTER通过九层认知语料库构建，将异构数据转化为可重用的经验资产，增强智能体的决策能力。
- 实验结果显示，KUPAS MASTER智能体在多个评分维度上均优于原始语料检索增强生成（RAG），提升幅度达9.83分。
📝 摘要（中文）
经验丰富的专业人士不仅了解事实和结论，还掌握重要线索、合理判断和行动选择。然而，常规工作记录往往缺乏这种隐性知识，导致大型语言模型（LLM）智能体无法有效利用专业经验。为此，本文提出了KUPAS MASTER，一个围绕九层认知语料库构建的经验工程平台。该平台将异构工作记录和从业者访谈转化为可追溯、可重用的经验语料库，并通过六个案例元素保留任务过程。通过对20名随机选取的从业者的授权样本进行处理，平台成功生成了23,024条个体经验记录和13,113个组织资产，显著提升了智能体在多个专业领域的表现。
🔬 方法详解
问题定义：本文旨在解决如何将专业人士的隐性知识有效转化为智能体可用的经验语料库。现有方法在捕捉和利用这些知识方面存在显著不足。
核心思路：KUPAS MASTER通过构建九层认知语料库，将异构工作记录和访谈数据整合为可追溯的经验资产，确保智能体能够利用这些知识进行有效决策。
技术框架：该平台的整体架构包括数据收集、语料库构建、经验提取和智能体能力增强四个主要模块。每个模块负责不同的任务，确保数据的完整性和可用性。
关键创新：KUPAS MASTER的最大创新在于其九层认知语料库的构建方法，能够系统性地提取和组织隐性知识，与传统方法相比，提供了更为丰富和结构化的知识表示。
关键设计：平台设计了六个知识库，包括规则、约束、最佳实践、负面示例、边界案例和技能，确保经验的多维度存储和调用，同时保留源证据和使用条件。
🖼️ 关键图片
📊 实验亮点
在实验中，KUPAS MASTER智能体在多个专业领域的表现显著优于基线模型，基础模型、原始语料检索增强生成（RAG）和KUPAS MASTER智能体的得分分别为70.63、79.75和89.58，提升幅度达到9.83分，显示出其在知识转化和应用方面的强大能力。
🎯 应用场景
KUPAS MASTER的研究成果可广泛应用于多个领域，如医疗、工程、教育等，帮助组织将个体的隐性知识转化为可共享的经验资产，提升智能体的决策能力和执行效率。未来，该平台有望推动知识管理和智能体技术的进一步发展。
📄 摘要（原文）
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: context, cues, judgment, action, boundaries, and outcomes. Nine-layer cognitive corpus construction organizes tacit experience along nine extraction dimensions and stores the resulting assets in six libraries: rules, constraints, best practices, negative examples, corner cases, and skills. Semantic alignment, individual experience distillation, organizational consolidation, and cross-review preserve source evidence, conditions of use, and unresolved disagreements. The platform packages these assets into callable skills with explicit inputs, steps, dependencies, and stopping conditions, connecting experience collection to task execution and evaluation feedback. Using authorized samples from 20 randomly selected practitioners, the platform processed 1,576 source files into 23,024 individual experience records and 13,113 organizational assets. The evaluation spans multiple professional domains. Under common task inputs and scoring criteria, the base model, raw corpus retrieval-augmented generation (RAG), and KUPAS MASTER agent scored 70.63, 79.75, and 89.58, respectively. The KUPAS MASTER agent improved on raw-corpus RAG in all seven scoring dimensions. The platform provides a practical path from individual tacit experience to organizational knowledge and agent capabilities.