AutoPal: Autonomous Adaptation to Users for Personal AI Companionship
This addresses the need for more personalized and evolving AI companionship for users, though it appears incremental as it builds on prior work in AI agents for emotional support.
The paper tackles the problem of enabling autonomous adaptation in personal AI companions to provide tailored emotional support, and the result is a hierarchical framework called AutoPal that facilitates controllable persona adjustments based on user interactions, with effectiveness demonstrated through extensive experiments.
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.