HasMem：面向长期LLM智能体的硬源自适应软化记忆

中文摘要 AI 辅助

基于文本的记忆和上下文压缩支持对过去交互的复用。调整连续记忆会改变冻结LLM的输入，将容量分配与读出耦合。我们提出硬源自适应软化记忆（HasMem）。冻结的硬提示嵌入提供了可验证的初始状态。一个控制器调整记忆宽度，一个写入器对调整大小的条目进行重新编码，而读取器和全局模块提供读出适应和跨轮次状态。在源自多会话聊天（MSC）开发集的重建探针的所有535个问题上，主配置在硬参考的框架记忆位置的93.6%处达到了95.3的词汇F1（+4.4个百分点）。在每问题目标主体预算大致匹配的情况下，六个配置在平均每条目保留率约0.83–0.91时，超过基于规则的重新编码8.0–23.6个精确匹配（EM）百分点。在固定模型参数和规则目标宽度比0.75的情况下，全局模块的EM增益在八次比较中通过了用户级精确配对检验（Bonferroni校正）。在全部500个LongMemEval-S问题上，局部词汇F1从硬参考的3.4上升到8.9，答案负对数似然（NLL）从12.257下降到5.274。在两个评估中，F1增益伴随着较低的EM。

英文摘要

Text-based memory and context compression support reuse of past interactions. Resizing continuous memory changes the input to a frozen LLM, coupling capacity allocation with readout. We propose Hard-Origin Adaptively Softened Memory (HasMem). Frozen hard-prompt embeddings provide a verifiable initial state. A controller adjusts memory widths, a Writer re-encodes resized entries, and Reader and Global provide readout adaptation and cross-turn state. On all $535$ questions in a reconstruction probe derived from the Multi-Session Chat (MSC) development split, the main configuration achieves lexical F1 of $95.3$ ($+4.4$ percentage points) at $93.6\%$ of the hard reference's framed memory positions. With approximately matched per-question target body budgets, six configurations at mean per-entry retention around $0.83$--$0.91$ exceed rule-based re-encoding by $8.0$--$23.6$ exact-match (EM) percentage points. With fixed model parameters and rule target width ratio $0.75$, Global's EM gain passes a user-level exact paired test with Bonferroni correction over eight comparisons. On all $500$ LongMemEval-S questions, local lexical F1 rises from the hard reference's $3.4$ to $8.9$, and answer negative log-likelihood (NLL) falls from $12.257$ to $5.274$. F1 gains accompany lower EM on both evaluations.

发表机构

• The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））
• University of Bristol（布里斯托大学）
• The Hong Kong University of Science and Technology（香港科技大学）

机构由 AI 辅助整理，请以论文原文为准。