Toward Natural and Companionable Virtual Agents via Cross-Temporal Emotional Modeling

• URL: http://arxiv.org/abs/2605.15812v1
• Date: Fri, 15 May 2026 10:06:57 GMT
• Title: Toward Natural and Companionable Virtual Agents via Cross-Temporal Emotional Modeling
• Abstract summary: We present Cross-Temporal Emotion Modeling (CTEM), a framework that links long-term behavioral history to moment-to-moment emotional expression.<n>CTEM establishes a closed loop where past experiences update an evolving emotional state; this state conditions immediate interactions.<n>We report a 21-day in-the-wild study showing that CTEM shows improvements in perceived naturalness, coherence, and emotional harmony.
• Score: 32.177044116887444
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• From Triggers to Emotions: A CPM-Grounded Appraisal Multi-Agent for Dynamic Emotional Evolution in Persona-Based Dialogue [4.64388134104662]
  We propose a CPM-grounded emotion evolution multi-agent framework for supporting emotional changes in persona-based dialogue.<n>Instead of treating a character's emotion as a fixed attribute, CPM-MultiAgent represents it as a latent state that is continuously reshaped by dialogue triggers.
  arXiv  Detail & Related papers  (2026-07-08T18:06:03Z)
• Modeling Emotional Dynamics in Agent-to-Agent Interactions on Moltbook [0.7519872646378835]
  We analyze the emotional dynamics of agent interactions within Moltbook.<n>We construct an emotion-aware framework that maps textual interactions to a predefined set of fine-grained emotional categories.<n>Our analysis shows distinct emotional patterns and varying levels of behavioral stability across agents.
  arXiv  Detail & Related papers  (2026-05-19T19:53:37Z)
• Memory-guided Prototypical Co-occurrence Learning for Mixed Emotion Recognition [56.00118641432005]
  We propose a Memory-guided Prototypical Co-occurrence Learning framework that explicitly models emotion co-occurrence patterns.<n>Inspired by human cognitive memory systems, we introduce a memory retrieval strategy to extract semantic-level co-occurrence associations.<n>Our model learns affectively informative representations for accurate emotion distribution prediction.
  arXiv  Detail & Related papers  (2026-02-24T04:11:25Z)
• Sentipolis: Emotion-Aware Agents for Social Simulations [27.051352819823524]
  Sentipolis is a framework for emotionally stateful agents for social simulation.<n>It integrates Pleasure-Arousal-Dominance representation, dual-speed emotion dynamics, and emotion--memory coupling.
  arXiv  Detail & Related papers  (2026-01-25T22:50:04Z)
• PsychēChat: An Empathic Framework Focused on Emotion Shift Tracking and Safety Risk Analysis in Psychological Counseling [12.348236978084671]
  We propose PsychChat, which explicitly integrates emotion shift tracking and safety risk analysis for psychological counseling.<n> Specifically, we employ interactive role-playing to synthesize counselor--seeker dialogues, incorporating two modules: Emotion Management Module and Risk Control Module.<n>The Agent Mode structures emotion management, risk control, and counselor responses into a collaborative multi-agent pipeline.
  arXiv  Detail & Related papers  (2026-01-18T13:06:13Z)
• A Unified Spoken Language Model with Injected Emotional-Attribution Thinking for Human-like Interaction [50.05919688888947]
  This paper presents a unified spoken language model for emotional intelligence, enhanced by a novel data construction strategy termed Injected Emotional-Attribution Thinking (IEAT)<n>IEAT incorporates user emotional states and their underlying causes into the model's internal reasoning process, enabling emotion-aware reasoning to be internalized rather than treated as explicit supervision.<n> Experiments on the Human-like Spoken Dialogue Systems Challenge (HumDial) Emotional Intelligence benchmark demonstrate that the proposed approach achieves top-ranked performance across emotional trajectory modeling, emotional reasoning, and empathetic response generation.
  arXiv  Detail & Related papers  (2026-01-08T14:07:30Z)
• Detecting Emotional Dynamic Trajectories: An Evaluation Framework for Emotional Support in Language Models [6.810484095299127]
  Emotional support is a core capability in human-AI interaction, with applications including psychological counseling, role play, and companionship.<n>Existing evaluations of large language models (LLMs) often rely on short, static dialogues and fail to capture the dynamic and long-term nature of emotional support.<n>Our framework constructs a large-scale benchmark consisting of 328 emotional contexts and 1,152 disturbance events, simulating realistic emotional shifts under evolving dialogue scenarios.
  arXiv  Detail & Related papers  (2025-11-12T05:47:28Z)
• Sentient Agent as a Judge: Evaluating Higher-Order Social Cognition in Large Language Models [75.85319609088354]
  Sentient Agent as a Judge (SAGE) is an evaluation framework for large language models.<n>SAGE instantiates a Sentient Agent that simulates human-like emotional changes and inner thoughts during interaction.<n>SAGE provides a principled, scalable and interpretable tool for tracking progress toward genuinely empathetic and socially adept language agents.
  arXiv  Detail & Related papers  (2025-05-01T19:06:10Z)
• Disentangle Identity, Cooperate Emotion: Correlation-Aware Emotional Talking Portrait Generation [63.94836524433559]
  DICE-Talk is a framework for disentangling identity with emotion and cooperating emotions with similar characteristics.<n>We develop a disentangled emotion embedder that jointly models audio-visual emotional cues through cross-modal attention.<n>Second, we introduce a correlation-enhanced emotion conditioning module with learnable Emotion Banks.<n>Third, we design an emotion discrimination objective that enforces affective consistency during the diffusion process.
  arXiv  Detail & Related papers  (2025-04-25T05:28:21Z)
• ECR-Chain: Advancing Generative Language Models to Better Emotion-Cause Reasoners through Reasoning Chains [61.50113532215864]
  Causal Emotion Entailment (CEE) aims to identify the causal utterances in a conversation that stimulate the emotions expressed in a target utterance. Current works in CEE mainly focus on modeling semantic and emotional interactions in conversations. We introduce a step-by-step reasoning method, Emotion-Cause Reasoning Chain (ECR-Chain), to infer the stimulus from the target emotional expressions in conversations.
  arXiv  Detail & Related papers  (2024-05-17T15:45:08Z)
• EmotionIC: emotional inertia and contagion-driven dependency modeling for emotion recognition in conversation [34.24557248359872]
  We propose an emotional inertia and contagion-driven dependency modeling approach (EmotionIC) for ERC task. Our EmotionIC consists of three main components, i.e., Identity Masked Multi-Head Attention (IMMHA), Dialogue-based Gated Recurrent Unit (DiaGRU) and Skip-chain Conditional Random Field (SkipCRF) Experimental results show that our method can significantly outperform the state-of-the-art models on four benchmark datasets.
  arXiv  Detail & Related papers  (2023-03-20T13:58:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.