AutoPal: Autonomous Adaptation to Users for Personal AI Companionship

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Cheng, Yi, Liu, Wenge, Xu, Kaishuai, Hou, Wenjun, Ouyang, Yi, Leong, Chak Tou, Li, Wenjie, Wu, Xian, Zheng, Yefeng
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866916783203549184
author Cheng, Yi
Liu, Wenge
Xu, Kaishuai
Hou, Wenjun
Ouyang, Yi
Leong, Chak Tou
Li, Wenjie
Wu, Xian
Zheng, Yefeng
author_facet Cheng, Yi
Liu, Wenge
Xu, Kaishuai
Hou, Wenjun
Ouyang, Yi
Leong, Chak Tou
Li, Wenjie
Wu, Xian
Zheng, Yefeng
contents Previous research has demonstrated the potential of AI agents to act as companions that can provide constant emotional support for humans. In this paper, we emphasize the necessity of autonomous adaptation in personal AI companionship, an underexplored yet promising direction. Such adaptability is crucial as it can facilitate more tailored interactions with users and allow the agent to evolve in response to users' changing needs. However, imbuing agents with autonomous adaptability presents unique challenges, including identifying optimal adaptations to meet users' expectations and ensuring a smooth transition during the adaptation process. To address them, we devise a hierarchical framework, AutoPal, that enables controllable and authentic adjustments to the agent's persona based on user interactions. A personamatching dataset is constructed to facilitate the learning of optimal persona adaptations. Extensive experiments demonstrate the effectiveness of AutoPal and highlight the importance of autonomous adaptability in AI companionship.
format Preprint
id arxiv_https___arxiv_org_abs_2406_13960
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle AutoPal: Autonomous Adaptation to Users for Personal AI Companionship
Cheng, Yi
Liu, Wenge
Xu, Kaishuai
Hou, Wenjun
Ouyang, Yi
Leong, Chak Tou
Li, Wenjie
Wu, Xian
Zheng, Yefeng
Computation and Language
Artificial Intelligence
Previous research has demonstrated the potential of AI agents to act as companions that can provide constant emotional support for humans. In this paper, we emphasize the necessity of autonomous adaptation in personal AI companionship, an underexplored yet promising direction. Such adaptability is crucial as it can facilitate more tailored interactions with users and allow the agent to evolve in response to users' changing needs. However, imbuing agents with autonomous adaptability presents unique challenges, including identifying optimal adaptations to meet users' expectations and ensuring a smooth transition during the adaptation process. To address them, we devise a hierarchical framework, AutoPal, that enables controllable and authentic adjustments to the agent's persona based on user interactions. A personamatching dataset is constructed to facilitate the learning of optimal persona adaptations. Extensive experiments demonstrate the effectiveness of AutoPal and highlight the importance of autonomous adaptability in AI companionship.
title AutoPal: Autonomous Adaptation to Users for Personal AI Companionship
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2406.13960