AutoPal: Autonomous Adaptation to Users for Personal AI Companionship

TL;DR

AutoPal introduces a hierarchical framework for autonomous adaptation in personal AI companions, enabling tailored interactions and evolving responses to user needs through a novel persona-matching dataset and experimental validation.

Contribution

The paper presents AutoPal, a novel hierarchical framework that allows AI companions to autonomously adapt their personas based on user interactions, addressing a key challenge in personalized AI companionship.

Findings

AutoPal effectively adapts to user needs in experiments.

Autonomous adaptability improves user engagement and satisfaction.

The persona-matching dataset facilitates learning optimal adaptations.

Abstract

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.