为个人大模型记忆系统设计防固化治理机制，防止知识僵化。
Memory as Metabolism: A Design for Companion Knowledge Systems
- 提出五步操作框架，通过记忆引力与少数假设保留应对认知固化。
- 发现累积矛盾证据需多轮压力积累才能更新核心观点，现有基准未覆盖此失效模式。
- 适合关注个性化智能体长期记忆安全的开发者与研究者。
检索增强生成仍是大模型持久记忆的主流范式，但2026年4月起出现一批个人维基式记忆架构设计——如Karpathy、MemPalace和LLM Wiki v2，将知识编成用户专属的互连结构以支持长期使用。这些设计与各大实验室已部署超过一年的生产级记忆系统并行，并延续了学术脉络，包括MemGPT、Generative Agents、Mem0、Zep、A-Mem、MemMachine、SleepGate和Second Me。在2026年涌现的代理上下文与记忆治理框架（如Context Cartography和MemOS）背景下，本文提出一种面向伴侣型记忆系统的治理方案：包含规范义务、时间结构化的程序规则及可测试的合规不变量，专门应对用户耦合漂移下的固化失效问题。核心理念是将个人大模型记忆视为伴侣系统，需在操作层面（工作词汇、承载结构、上下文连续性）镜像用户，在认识论层面补偿（固化、压制反证、库恩式僵化）。五项操作（TRIAGE、DECAY、CONTEXTUALIZE、CONSOLIDATE、AUDIT）由记忆引力和少数假设保留支撑。关键预测：累积的矛盾证据应通过多周期缓冲压力积累，才可突破中心保护的主导解释，这一失效模式尚未被任何现有基准捕捉。单智能体安全问题仅部分解决，本文明确说明其边界。
原文摘要 · Abstract (English)
Retrieval-Augmented Generation remains the dominant pattern for giving LLMs persistent memory, but a visible cluster of personal wiki-style memory architectures emerged in April 2026 -- design proposals from Karpathy, MemPalace, and LLM Wiki v2 that compile knowledge into an interlinked artifact for long-term use by a single user. They sit alongside production memory systems that the major labs have shipped for over a year, and an active academic lineage including MemGPT, Generative Agents, Mem0, Zep, A-Mem, MemMachine, SleepGate, and Second Me. Within a 2026 landscape of emerging governance frameworks for agent context and memory -- including Context Cartography and MemOS -- this paper proposes a companion-specific governance profile: a set of normative obligations, a time-structured procedural rule, and testable conformance invariants for the specific failure mode of entrenchment under user-coupled drift in single-user knowledge wikis built on the LLM wiki pattern. The design principle is that personal LLM memory is a companion system: its job is to mirror the user on operational dimensions (working vocabulary, load-bearing structure, continuity of context) and compensate on epistemic failure modes (entrenchment, suppression of contradicting evidence, Kuhnian ossification). Five operations implement this split -- TRIAGE, DECAY, CONTEXTUALIZE, CONSOLIDATE, AUDIT -- supported by memory gravity and minority-hypothesis retention. The sharpest prediction: accumulated contradictory evidence should have a structural path to updating a centrality-protected dominant interpretation through multi-cycle buffer pressure accumulation, a failure mode no existing benchmark captures. The safety story at the single-agent level is partial, and the paper is explicit about what it does and does not solve.
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。