A Grounded Memory System For Smart Personal Assistants
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916729525895168 |
|---|---|
| author | Ocker, Felix Deigmöller, Jörg Smirnov, Pavel Eggert, Julian |
| author_facet | Ocker, Felix Deigmöller, Jörg Smirnov, Pavel Eggert, Julian |
| contents | A wide variety of agentic AI applications - ranging from cognitive assistants for dementia patients to robotics - demand a robust memory system grounded in reality. In this paper, we propose such a memory system consisting of three components. First, we combine Vision Language Models for image captioning and entity disambiguation with Large Language Models for consistent information extraction during perception. Second, the extracted information is represented in a memory consisting of a knowledge graph enhanced by vector embeddings to efficiently manage relational information. Third, we combine semantic search and graph query generation for question answering via Retrieval Augmented Generation. We illustrate the system's working and potential using a real-world example. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_06328 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Grounded Memory System For Smart Personal Assistants Ocker, Felix Deigmöller, Jörg Smirnov, Pavel Eggert, Julian Artificial Intelligence H.3.3; H.3.4; I.2.1; I.2.5; I.2.7; I.2.10; J.3 A wide variety of agentic AI applications - ranging from cognitive assistants for dementia patients to robotics - demand a robust memory system grounded in reality. In this paper, we propose such a memory system consisting of three components. First, we combine Vision Language Models for image captioning and entity disambiguation with Large Language Models for consistent information extraction during perception. Second, the extracted information is represented in a memory consisting of a knowledge graph enhanced by vector embeddings to efficiently manage relational information. Third, we combine semantic search and graph query generation for question answering via Retrieval Augmented Generation. We illustrate the system's working and potential using a real-world example. |
| title | A Grounded Memory System For Smart Personal Assistants |
| topic | Artificial Intelligence H.3.3; H.3.4; I.2.1; I.2.5; I.2.7; I.2.10; J.3 |
| url | https://arxiv.org/abs/2505.06328 |