AME: An Efficient Heterogeneous Agentic Memory Engine for Smartphones
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909921328496640 |
|---|---|
| author | Zhao, Xinkui Ma, Qingyu Zhang, Yifan Lou, Hengxuan Cheng, Guanjie Deng, Shuiguang Yin, Jianwei |
| author_facet | Zhao, Xinkui Ma, Qingyu Zhang, Yifan Lou, Hengxuan Cheng, Guanjie Deng, Shuiguang Yin, Jianwei |
| contents | On-device agents on smartphones increasingly require continuously evolving memory to support personalized, context-aware, and long-term behaviors. To meet both privacy and responsiveness demands, user data is embedded as vectors and stored in a vector database for fast similarity search. However, most existing vector databases target server-class environments. When ported directly to smartphones, two gaps emerge: (G1) a mismatch between mobile SoC constraints and vector-database assumptions, including tight bandwidth budgets, limited on-chip memory, and stricter data type and layout constraints; and (G2) a workload mismatch, because on-device usage resembles a continuously learning memory, in which queries must coexist with frequent inserts, deletions, and ongoing index maintenance. To address these challenges, we propose AME, an on-device Agentic Memory Engine co-designed with modern smartphone SoCs. AME introduces two key techniques: (1) a hardware-aware, high-efficiency matrix pipeline that maximizes compute-unit utilization and exploits multi-level on-chip storage to sustain high throughput; and (2) a hardware- and workload-aware scheduling scheme that coordinates querying, insertion, and index rebuilding to minimize latency. We implement AME on Snapdragon 8-series SoCs and evaluate it on HotpotQA. In our experiments, AME improves query throughput by up to 1.4x at matched recall, achieves up to 7x faster index construction, and delivers up to 6x higher insertion throughput under concurrent query workloads. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_19192 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | AME: An Efficient Heterogeneous Agentic Memory Engine for Smartphones Zhao, Xinkui Ma, Qingyu Zhang, Yifan Lou, Hengxuan Cheng, Guanjie Deng, Shuiguang Yin, Jianwei Distributed, Parallel, and Cluster Computing On-device agents on smartphones increasingly require continuously evolving memory to support personalized, context-aware, and long-term behaviors. To meet both privacy and responsiveness demands, user data is embedded as vectors and stored in a vector database for fast similarity search. However, most existing vector databases target server-class environments. When ported directly to smartphones, two gaps emerge: (G1) a mismatch between mobile SoC constraints and vector-database assumptions, including tight bandwidth budgets, limited on-chip memory, and stricter data type and layout constraints; and (G2) a workload mismatch, because on-device usage resembles a continuously learning memory, in which queries must coexist with frequent inserts, deletions, and ongoing index maintenance. To address these challenges, we propose AME, an on-device Agentic Memory Engine co-designed with modern smartphone SoCs. AME introduces two key techniques: (1) a hardware-aware, high-efficiency matrix pipeline that maximizes compute-unit utilization and exploits multi-level on-chip storage to sustain high throughput; and (2) a hardware- and workload-aware scheduling scheme that coordinates querying, insertion, and index rebuilding to minimize latency. We implement AME on Snapdragon 8-series SoCs and evaluate it on HotpotQA. In our experiments, AME improves query throughput by up to 1.4x at matched recall, achieves up to 7x faster index construction, and delivers up to 6x higher insertion throughput under concurrent query workloads. |
| title | AME: An Efficient Heterogeneous Agentic Memory Engine for Smartphones |
| topic | Distributed, Parallel, and Cluster Computing |
| url | https://arxiv.org/abs/2511.19192 |