# A Grounded Memory System For Smart Personal Assistants

Source: [A Grounded Memory System For Smart Personal Assistants](<https://www.sota2.com/research/paper/68fa78761e209131cea78797>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T04:39:15.781Z

Authors: Felix Ocker, J\\"org Deigm\\"oller, Pavel Smirnov, Julian Eggert

Published: 2025-05-09T10:08:22.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2505.06328>)

[PDF](<https://arxiv.org/pdf/2505.06328.pdf>)
