个性化LLM智能体记忆的生物特征方法

中文摘要 AI 辅助

个性化记忆通过存储和跨交互复用用户特定数据，帮助LLM智能体提供稳定且量身定制的协助。然而，在多用户场景中，检索不仅要考虑语义相似性，还要考虑当前请求者是否与存储记忆关联的身份匹配。我们提出Bio-Memory，一种生物特征感知的记忆架构，该架构将记忆检索同时基于语义相似性和生物特征匹配。Bio-Memory构建在A-Mem之上，为每个原子记忆笔记增加一个生物特征嵌入，并在语义排序之前使用生物特征匹配形成检索候选池。我们在LoCoMo上以10用户共享智能体设置下，在7个人脸基准和10个掌纹协议上评估Bio-Memory。跨数据集，Bio-Memory一致地分离所有者和非所有者查询。在人脸个性化下，最大平均差距在CALFW上达到F1/BLEU-1的27.29%/21.15%；在掌纹个性化下，相应差距在MS_Blue上为25.75%/19.22%。这些结果支持生物特征作为共享环境中个性化记忆检索的实际控制信号。

英文摘要

Personalized memory helps LLM agents deliver stable, tailored assistance by storing and reusing user-specific data across interactions. In multi-user scenarios, however, retrieval must consider not only semantic similarity but also whether the current requester matches the identity associated with the stored memory. We propose Bio-Memory, a biometric-aware memory architecture that conditions memory retrieval on both semantic similarity and biometric matching. Built on top of A-Mem, Bio-Memory augments each atomic memory note with a biometric embedding and uses biometric matching to form the retrieval candidate pool before semantic ranking. We evaluate Bio-Memory on LoCoMo in a 10-user shared-agent setting over 7 face benchmarks and 10 palmprint protocols. Across datasets, Bio-Memory consistently separates owner and non-owner queries. Under face-based personalization, the largest average gap reaches 27.29% / 21.15% in F1 / BLEU-1 on CALFW; under palmprint-based personalization, the corresponding gap is 25.75% / 19.22% on MS_Blue. These results support biometrics as a practical control signal for personalized memory retrieval in shared environments.

发表机构

• Anhui University（安徽大学）
• National Institute of Informatics（信息学研究所）

机构由 AI 辅助整理，请以论文原文为准。