发表机构
University of Oldenburg; Computational Intelligence Lab（奥尔登堡大学; 计算智能实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对大语言模型缺乏显式紧凑演化概念表示机制的问题，提出基于算子的 3M 框架，通过心智模型整合新信息，可完成知识提取、更新等操作，以进化策略为例说明其运行逻辑。
AI 中文摘要
大语言模型可处理海量信息，但通常缺乏用于维护紧凑且演化的概念表示的显式机制。我们提出心智模型管理（3M）框架，该框架将知识表示为包含紧凑块的心智模型。3M 不累积文本段落，而是持续将新信息整合到现有概念表示中。一组算子可提取知识、检索相关模型、添加与更新块、重组表示、检测不一致性及推导新知识。我们描述了 3M 的主要算子，并以进化策略为运行示例说明各操作。
英文摘要
Large language models process large amounts of information but usually lack an explicit mechanism for maintaining compact and evolving conceptual representations. We introduce Mental Model Management (3M), a framework in which knowledge is represented as mental models consisting of compact chunks. Rather than accumulating text passages, 3M continuously integrates new information into an existing conceptual representation. A set of operators extracts knowledge, retrieves relevant models, adds and updates chunks, reorganizes representations, detects inconsistencies, and derives new knowledge. We describe the main 3M operators and illustrate each operation using Evolution Strategies as a running example.
