Saved in:
Bibliographic Details
Main Authors: Qin, Feier, Li, Xiao, Zheng, Yi, Huang, Haibin, Wang, Hanyao, Wang, Xiaoyu, Lu, Yan, Zhang, Yuan
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.15812
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910223640297472
author Qin, Feier
Li, Xiao
Zheng, Yi
Huang, Haibin
Wang, Hanyao
Wang, Xiaoyu
Lu, Yan
Zhang, Yuan
author_facet Qin, Feier
Li, Xiao
Zheng, Yi
Huang, Haibin
Wang, Hanyao
Wang, Xiaoyu
Lu, Yan
Zhang, Yuan
contents Recent advances in foundation models have enabled conversational agents that aim for sustained companionship rather than mere task completion. Yet most still remain unable to support natural, long-term companion-like interactions, resulting in experiences that feel episodic and inauthentic. We argue that current agents overlooked cross-temporal modeling of agents' social behaviors and internal emotions: generated behaviors rarely influence an agent's emotional state, and emotional states seldom shape subsequent behaviors. We present Cross-Temporal Emotion Modeling (CTEM), a framework that links long-term behavioral history to moment-to-moment emotional expression. CTEM establishes a closed loop where past experiences update an evolving emotional state; this state conditions immediate interactions; and user feedback continually revises both memory and emotional state, enabling reflection and anticipation. We instantiate CTEM as Auri, a companion agent on an instant-messaging platform, and report a 21-day in-the-wild study showing that CTEM shows improvements in perceived naturalness, coherence, and emotional harmony.
format Preprint
id arxiv_https___arxiv_org_abs_2605_15812
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Toward Natural and Companionable Virtual Agents via Cross-Temporal Emotional Modeling
Qin, Feier
Li, Xiao
Zheng, Yi
Huang, Haibin
Wang, Hanyao
Wang, Xiaoyu
Lu, Yan
Zhang, Yuan
Human-Computer Interaction
Artificial Intelligence
Recent advances in foundation models have enabled conversational agents that aim for sustained companionship rather than mere task completion. Yet most still remain unable to support natural, long-term companion-like interactions, resulting in experiences that feel episodic and inauthentic. We argue that current agents overlooked cross-temporal modeling of agents' social behaviors and internal emotions: generated behaviors rarely influence an agent's emotional state, and emotional states seldom shape subsequent behaviors. We present Cross-Temporal Emotion Modeling (CTEM), a framework that links long-term behavioral history to moment-to-moment emotional expression. CTEM establishes a closed loop where past experiences update an evolving emotional state; this state conditions immediate interactions; and user feedback continually revises both memory and emotional state, enabling reflection and anticipation. We instantiate CTEM as Auri, a companion agent on an instant-messaging platform, and report a 21-day in-the-wild study showing that CTEM shows improvements in perceived naturalness, coherence, and emotional harmony.
title Toward Natural and Companionable Virtual Agents via Cross-Temporal Emotional Modeling
topic Human-Computer Interaction
Artificial Intelligence
url https://arxiv.org/abs/2605.15812