用生物特征区分用户，让AI记住谁的偏好
Personalizing LLM Agent Memory Using Biometrics
- 在记忆检索中加入生物特征匹配，防止信息混淆
- 人脸和掌纹识别下，主人与非主人查询准确率差距超25%
- 适合多人共享AI助手的隐私保护场景
个性化记忆能帮助大模型智能体通过存储和复用用户特定数据，在多轮交互中提供稳定、定制化的服务。但在多用户场景中，检索不仅需考虑语义相似性，还需判断当前请求者是否与记忆所关联的身份一致。我们提出Bio-Memory，一种基于生物特征的记忆架构，将记忆检索同时基于语义相似性和生物特征匹配。该架构在A-Mem基础上，为每个记忆条目增加生物特征嵌入，并先通过生物特征匹配筛选候选池，再进行语义排序。我们在10用户共享代理设置下，于LoCoMo数据集上评估了10种掌纹协议和7个面部识别基准。结果表明，无论在人脸或掌纹个性化下，系统均能有效区分主人与非主人查询。在人脸个性化下，CALFW数据集上F1与BLEU-1指标的最大平均差距分别为27.29%和21.15%；掌纹个性化下，MS_Blue数据集对应差距为25.75%和19.22%。这些结果验证了生物特征作为共享环境中个性化记忆检索的实用控制信号。
原文摘要 · Abstract (English)
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.
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。