mlsanityData to 14 Oct 2026

From Momentary Emotion Inference to Sustained Emotion Support: Evaluating a Companion Agent in a Longitudinal Study

arXiv 2609.16344 ↗First posted 14 Sep 2026cs.HC cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Sustained emotional support is a long-horizon interaction task closely tied to human well-being. Recent research demonstrates generative agents' capacity for momentary emotional support, yet how these capabilities sustain support over time remains unclear. To examine this challenge, we deployed PAIR, a theory-based emotion-regulation companion, with 19 participants for 14 days. Across 1,093 sessions, we paired emotion estimates with self-reports before and after guidance and analyzed logs and interviews. Estimates corresponded more closely to self-reported valence and dominance than arousal. Guided conversations were followed by higher valence and state-dependent arousal changes. Participants felt understood through contextual exploration and emotional acknowledgment, acting on guidance suited to their needs and constraints. Perceived helpfulness of guided conversation significantly increased over time. Our findings link memory updates and retained corrections to cross-session personalization, informing future emotional support tools that adapt to evolving needs, learn from prior outcomes, and preserve user control over memory.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 33 of its 106 references that are in the map. First posted on arXiv 14 Sep 2026.

Builds on

33 of 106 references.

References · 33

  1. 2023ChatGPT Outperforms Crowd-Workers for Text-Annotation Taskscited by 870
  2. 2024Evaluating Very Long-Term Conversational Memory of LLM Agentscited by 830
  3. 2024LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memorycited by 707
  4. 2021Towards Emotional Support Dialog Systemscited by 299
  5. 2023Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theorycited by 230
  6. 2025Know Me, Respond to Me: Benchmarking LLMs for Dynamic User Profiling and Personalized Responses at Scalecited by 178
  7. 2023Eliciting Human Preferences with Language Modelscited by 92
  8. 2023Cognitive Reframing of Negative Thoughts through Human-Language Model Interactioncited by 77
  9. 2022Improving Multi-turn Emotional Support Dialogue Generation with Lookahead Strategy Planningcited by 60
  10. 2023"It's a Fair Game", or Is It? Examining How Users Navigate Disclosure Risks and Benefits When Using LLM-Based Conversational Agentscited by 60
  11. 2024Can Large Language Models be Good Emotional Supporter? Mitigating Preference Bias on Emotional Support Conversationcited by 55
  12. 2023Facilitating Self-Guided Mental Health Interventions Through Human-Language Model Interaction: A Case Study of Cognitive Restructuringcited by 53
21 more
  1. 2023MindfulDiary: Harnessing Large Language Model to Support Psychiatric Patients' Journalingcited by 50
  2. 2023Leveraging Large Language Models to Power Chatbots for Collecting User Self-Reported Datacited by 48
  3. 2024ESCoT: Towards Interpretable Emotional Support Dialogue Systemscited by 46
  4. 2023Memory Sandbox: Transparent and Interactive Memory Management for Conversational Agentscited by 36
  5. 2023ChaCha: Leveraging Large Language Models to Prompt Children to Share Their Emotions about Personal Eventscited by 31
  6. 2020K-EmoCon, a multimodal sensor dataset for continuous emotion recognition in naturalistic conversationscited by 30
  7. 2024GPTCoach: Towards LLM-Based Physical Activity Coachingcited by 29
  8. 2025Customizing Emotional Support: How Do Individuals Construct and Interact With LLM-Powered Chatbotscited by 25
  9. 2023Fine-grained Affective Processing Capabilities Emerging from Large Language Modelscited by 24
  10. 2024ComPeer: A Generative Conversational Agent for Proactive Peer Supportcited by 24
  11. 2024MindScape Study: Integrating LLM and Behavioral Sensing for Personalized AI-Driven Journaling Experiencescited by 24
  12. 2023VITA: A Multi-modal LLM-based System for Longitudinal, Autonomous, and Adaptive Robotic Mental Well-being Coachingcited by 13
  13. 2024Large Language Models are Capable of Offering Cognitive Reappraisal, if Guidedcited by 13
  14. 2023Investigating Large Language Models' Perception of Emotion Using Appraisal Theorycited by 12
  15. 2023Understanding the Role of Large Language Models in Personalizing and Scaffolding Strategies to Combat Academic Procrastinationcited by 12
  16. 2024APTNESS: Incorporating Appraisal Theory and Emotion Support Strategies for Empathetic Response Generationcited by 12
  17. 2025Understanding Users' Privacy Perceptions Towards LLM's RAG-based Memorycited by 6
  18. 2025Towards AI as Colleagues: Multi-Agent System Improves Structured Ideation Processescited by 6
  19. 2025Bloom: Designing for LLM-Augmented Behavior Change Interactionscited by 3
  20. 2026The Algorithmic Self-Portrait: Deconstructing Memory in ChatGPTcited by 2
  21. 2026Chatting with Confidants or Corporations? Privacy Management with AI Companionscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Toward Natural and Companionable Virtual Agents via Cross-Temporal Emotional Modeling
  2. 2026ENPMR-Bench: Benchmarking Proactive Memory Retrieval for Emotional Support Agents
  3. 2026TEA-Bench: A Systematic Benchmarking of Tool-enhanced Emotional Support Dialogue Agent
  4. 2025Teleology-Driven Affective Computing: A Causal Framework for Sustained Well-Being
  5. 2025Investigating AI in Peer Support via Multi-Module System-Driven Embodied Conversational Agents
  6. 2025ESC-Judge: A Framework for Comparing Emotional Support Conversational Agents
  7. 2026Sentipolis: Emotion-Aware Agents for Social Simulations
  8. 2025From Generic Empathy to Personalized Emotional Support: A Self-Evolution Framework for User Preference Alignment