A Multi-Memory Segment System for Generating High-Quality Long-Term Memory Content in Agents
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918488737579008 |
|---|---|
| author | Zhang, Gaoke Wang, Bo Ma, Yunlong Zhao, Dongming Yu, Zifei |
| author_facet | Zhang, Gaoke Wang, Bo Ma, Yunlong Zhao, Dongming Yu, Zifei |
| contents | In the current field of agent memory, extensive explorations have been conducted in the area of memory retrieval, yet few studies have focused on exploring the memory content. Most research simply stores summarized versions of historical dialogues, as exemplified by methods like A-MEM and MemoryBank. However, when humans form long-term memories, the process involves multi-dimensional and multi-component generation, rather than merely creating simple summaries. The low-quality memory content generated by existing methods can adversely affect recall performance and response quality. In order to better construct high-quality long-term memory content, we have designed a multi-memory segment system (MMS) inspired by cognitive psychology theory. The system processes short-term memory into multiple long-term memory segments, and constructs retrieval memory units and contextual memory units based on these segments, with a one-to-one correspondence between the two. During the retrieval phase, MMS will match the most relevant retrieval memory units based on the user's query. Then, the corresponding contextual memory units is obtained as the context for the response stage to enhance knowledge, thereby effectively utilizing historical data. We conducted experiments on the LoCoMo dataset and further performed ablation experiments, experiments on the robustness regarding the number of input memories, and overhead experiments, which demonstrated the effectiveness and practical value of our method. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_15294 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Multi-Memory Segment System for Generating High-Quality Long-Term Memory Content in Agents Zhang, Gaoke Wang, Bo Ma, Yunlong Zhao, Dongming Yu, Zifei Artificial Intelligence Computation and Language Multiagent Systems I.2.7 In the current field of agent memory, extensive explorations have been conducted in the area of memory retrieval, yet few studies have focused on exploring the memory content. Most research simply stores summarized versions of historical dialogues, as exemplified by methods like A-MEM and MemoryBank. However, when humans form long-term memories, the process involves multi-dimensional and multi-component generation, rather than merely creating simple summaries. The low-quality memory content generated by existing methods can adversely affect recall performance and response quality. In order to better construct high-quality long-term memory content, we have designed a multi-memory segment system (MMS) inspired by cognitive psychology theory. The system processes short-term memory into multiple long-term memory segments, and constructs retrieval memory units and contextual memory units based on these segments, with a one-to-one correspondence between the two. During the retrieval phase, MMS will match the most relevant retrieval memory units based on the user's query. Then, the corresponding contextual memory units is obtained as the context for the response stage to enhance knowledge, thereby effectively utilizing historical data. We conducted experiments on the LoCoMo dataset and further performed ablation experiments, experiments on the robustness regarding the number of input memories, and overhead experiments, which demonstrated the effectiveness and practical value of our method. |
| title | A Multi-Memory Segment System for Generating High-Quality Long-Term Memory Content in Agents |
| topic | Artificial Intelligence Computation and Language Multiagent Systems I.2.7 |
| url | https://arxiv.org/abs/2508.15294 |