HARMONI: Multimodal Personalization of Multi-User Human-Robot Interactions with LLMs

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Malécot, Jeanne, Rahimi, Hamed, Cattoni, Jeanne, Samson, Marie, Abrini, Mouad, Khoramshahi, Mahdi, Pino, Maribel, Chetouani, Mohamed
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910002518687744
author Malécot, Jeanne
Rahimi, Hamed
Cattoni, Jeanne
Samson, Marie
Abrini, Mouad
Khoramshahi, Mahdi
Pino, Maribel
Chetouani, Mohamed
author_facet Malécot, Jeanne
Rahimi, Hamed
Cattoni, Jeanne
Samson, Marie
Abrini, Mouad
Khoramshahi, Mahdi
Pino, Maribel
Chetouani, Mohamed
contents Existing human-robot interaction systems often lack mechanisms for sustained personalization and dynamic adaptation in multi-user environments, limiting their effectiveness in real-world deployments. We present HARMONI, a multimodal personalization framework that leverages large language models to enable socially assistive robots to manage long-term multi-user interactions. The framework integrates four key modules: (i) a perception module that identifies active speakers and extracts multimodal input; (ii) a world modeling module that maintains representations of the environment and short-term conversational context; (iii) a user modeling module that updates long-term speaker-specific profiles; and (iv) a generation module that produces contextually grounded and ethically informed responses. Through extensive evaluation and ablation studies on four datasets, as well as a real-world scenario-driven user-study in a nursing home environment, we demonstrate that HARMONI supports robust speaker identification, online memory updating, and ethically aligned personalization, outperforming baseline LLM-driven approaches in user modeling accuracy, personalization quality, and user satisfaction.
format Preprint
id arxiv_https___arxiv_org_abs_2601_19839
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle HARMONI: Multimodal Personalization of Multi-User Human-Robot Interactions with LLMs
Malécot, Jeanne
Rahimi, Hamed
Cattoni, Jeanne
Samson, Marie
Abrini, Mouad
Khoramshahi, Mahdi
Pino, Maribel
Chetouani, Mohamed
Robotics
Artificial Intelligence
Human-Computer Interaction
Existing human-robot interaction systems often lack mechanisms for sustained personalization and dynamic adaptation in multi-user environments, limiting their effectiveness in real-world deployments. We present HARMONI, a multimodal personalization framework that leverages large language models to enable socially assistive robots to manage long-term multi-user interactions. The framework integrates four key modules: (i) a perception module that identifies active speakers and extracts multimodal input; (ii) a world modeling module that maintains representations of the environment and short-term conversational context; (iii) a user modeling module that updates long-term speaker-specific profiles; and (iv) a generation module that produces contextually grounded and ethically informed responses. Through extensive evaluation and ablation studies on four datasets, as well as a real-world scenario-driven user-study in a nursing home environment, we demonstrate that HARMONI supports robust speaker identification, online memory updating, and ethically aligned personalization, outperforming baseline LLM-driven approaches in user modeling accuracy, personalization quality, and user satisfaction.
title HARMONI: Multimodal Personalization of Multi-User Human-Robot Interactions with LLMs
topic Robotics
Artificial Intelligence
Human-Computer Interaction
url https://arxiv.org/abs/2601.19839