AI 中文总结
KUPAS MASTER平台通过九层认知语料库构建，将从业者隐性经验提炼为可复用智能体语料，显著提升LLM智能体在专业任务中的表现。
AI 中文摘要
经验丰富的专业人士所掌握的远不止事实和结论。他们知道哪些线索至关重要、为何某个判断是合理的，以及应当采取何种行动。常规的工作记录往往遗漏了这种隐性知识，使得大型语言模型（LLM）智能体难以有效利用专业经验。我们提出了KUPAS MASTER，一个围绕九层认知语料库构建的经验工程平台。该平台将异构的工作记录和从业者访谈转化为可追溯、可复用的智能体经验语料库。六个案例要素保留了任务过程：情境、线索、判断、行动、边界和结果。九层认知语料库构建沿九个提取维度组织隐性经验，并将所得资产存储于六个库中：规则、约束、最佳实践、负面示例、边缘案例和技能。语义对齐、个体经验提炼、组织整合和交叉审查保留了源证据、使用条件和未解决的分歧。该平台将这些资产打包为可调用的技能，并明确其输入、步骤、依赖关系和停止条件，从而将经验收集与任务执行和评估反馈连接起来。使用来自20名随机选择的从业者的授权样本，该平台将1，576个源文件处理为23，024条个体经验记录和13，111条组织资产。评估覆盖多个专业领域。在共同的任务输入和评分标准下，基础模型、原始语料库检索增强生成（RAG）和KUPAS MASTER智能体的得分分别为70.63、79.75和89.58。KUPAS MASTER智能体在所有七个评分维度上均优于原始语料库RAG。该平台提供了一条从个体隐性经验到组织知识和智能体能力的实用路径。
英文摘要
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.
CommentsTechnical Report. Official website: https://lsf.kupasai.com/ Report homepage: https://tongjiai4e.github.io/KUPAS-MASTER-Report/
