让大模型像人一样动态管理概念，持续更新知识结构。
Mental Model Management: An Operator-Based Framework for LLM Memory
- 用操作符驱动的框架，将知识组织为可演化的心智模型
- 通过提取、更新、重组等操作，实现知识的持续整合与修正
- 适合需要长期推理和知识演化的复杂任务场景
大型语言模型处理海量信息，但缺乏显式的紧凑且可演进的概念表征机制。本文提出心智模型管理（Mental Model Management, 3M）框架，将知识表示为由紧凑模块构成的心智模型。3M不累积文本片段，而是持续将新信息融入现有概念表征。一组操作符负责提取知识、检索相关模型、添加与更新模块、重新组织表征、检测不一致，并推导新知识。本文描述了主要的3M操作符，并以进化策略（Evolution Strategies）为例说明各操作的实际应用。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。