"My agent understands me better": Integrating Dynamic Human-like Memory Recall and Consolidation in LLM-Based Agents
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866929298386976768 |
|---|---|
| author | Hou, Yuki Tamoto, Haruki Miyashita, Homei |
| author_facet | Hou, Yuki Tamoto, Haruki Miyashita, Homei |
| contents | In this study, we propose a novel human-like memory architecture designed for enhancing the cognitive abilities of large language model based dialogue agents. Our proposed architecture enables agents to autonomously recall memories necessary for response generation, effectively addressing a limitation in the temporal cognition of LLMs. We adopt the human memory cue recall as a trigger for accurate and efficient memory recall. Moreover, we developed a mathematical model that dynamically quantifies memory consolidation, considering factors such as contextual relevance, elapsed time, and recall frequency. The agent stores memories retrieved from the user's interaction history in a database that encapsulates each memory's content and temporal context. Thus, this strategic storage allows agents to recall specific memories and understand their significance to the user in a temporal context, similar to how humans recognize and recall past experiences. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_00573 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | "My agent understands me better": Integrating Dynamic Human-like Memory Recall and Consolidation in LLM-Based Agents Hou, Yuki Tamoto, Haruki Miyashita, Homei Human-Computer Interaction I.2.4; H.3.3 In this study, we propose a novel human-like memory architecture designed for enhancing the cognitive abilities of large language model based dialogue agents. Our proposed architecture enables agents to autonomously recall memories necessary for response generation, effectively addressing a limitation in the temporal cognition of LLMs. We adopt the human memory cue recall as a trigger for accurate and efficient memory recall. Moreover, we developed a mathematical model that dynamically quantifies memory consolidation, considering factors such as contextual relevance, elapsed time, and recall frequency. The agent stores memories retrieved from the user's interaction history in a database that encapsulates each memory's content and temporal context. Thus, this strategic storage allows agents to recall specific memories and understand their significance to the user in a temporal context, similar to how humans recognize and recall past experiences. |
| title | "My agent understands me better": Integrating Dynamic Human-like Memory Recall and Consolidation in LLM-Based Agents |
| topic | Human-Computer Interaction I.2.4; H.3.3 |
| url | https://arxiv.org/abs/2404.00573 |