The study evaluates PAIR, a theory-based emotion‑regulation companion, over 14 days with 19 participants, analyzing 1,093 sessions. Emotion estimates from the agent aligned better with participants’ self‑reported valence and dominance than arousal, and guided conversations led to higher valence and state‑dependent arousal changes. Participants reported feeling understood, and the perceived helpfulness of guided conversations increased over time, highlighting the role of memory updates and cross‑session personalization in sustained emotional support.
By Kexin Quan, Zijian Ding, Jiaye Yong, Qinshi Zhang, Dong Wang, Jessie Chin
arXiv:2607. 14593v1 Announce Type: cross Abstract: As conversational AI systems are designed for repeated use, a central question is how a series of interactions becomes a relationship.
By Ryuichi Sumida, Mao Saeki, Masaki Eguchi, Sadahiro Yoshikawa, Koji Inoue, Tatsuya Kawahara, Yoichi Matsuyama
Caregivers often turn to online communities for informational and emotional support. In these spaces, peer supporters frequently draw on personal narratives to respond to emotionally complex caregiving situations.
arXiv:2606. 18057v1 Announce Type: cross Abstract: Caregivers often turn to online communities for informational and emotional support.
By Drishti Goel, Violeta J. Rodriguez, Daniel S. Brown, Ravi Karkar, Dong Whi Yoo, Koustuv Saha
arXiv:2607. 17564v1 Announce Type: new Abstract: AI companions are judged not only by single-turn fluency but by whether they sustain emotional continuity: remembering who the companion is, what the user prefers, and how the relationship has felt.
By Jingzhe Fang, Guozhi Xu, Yunfan Cui, Xiaochen Yang, Zhangyu Hua
arXiv:2607. 24190v1 Announce Type: cross Abstract: Social robots that rely on large language models for conversation are unable to retain information across sessions.
By Steve Aschenbrenner, Marcel Heisler, Thomas Sievers, Christian Becker-Asano
arXiv:2609.17434v1 Announce Type: cross
Abstract: Family caregivers of people living with dementia shoulder emotional and practical responsibilities, yet their own wellbeing often remains peripheral...
By Jiayue Melissa Shi, Ethan Nguyen, Drishti Goel, Upasana Natarajan, Shashwat Srivatsa, Daniel S. Brown, Violeta J. Rodr\'iguez, Dong Whi Yoo, Ravi Karkar, Koustuv Saha
arXiv:2409.02244v3 Announce Type: replace-cross
Abstract: Large language models (LLMs) are increasingly being used as ad hoc therapists. While prior research has found that LLMs outperform human coun...
By Zainab Iftikhar, Sean Ransom, Amy Xiao, Nicole Nugent, Jeff Huang
The paper proposes a new class of relational AI called Significant Other Artificial Intelligence (SO‑AI), designed to emulate the stabilizing role of human significant others by providing identity awareness, long‑term memory, proactive support, narrative co‑construction, and ethical boundary enforcement. It outlines a conceptual architecture featuring an anthropomorphic interface, a relational cognition layer, and a governance layer, and presents a research agenda for evaluating identity stability, interaction patterns, narrative development, and sociocultural impact. The authors argue that SO‑AI could fill the relational anchor gap many people experience today, offering a blueprint for responsibly augmenting long‑term, identity‑bearing partnerships between humans and AI.
By Sung Park
arXiv:2606. 06055v1 Announce Type: new Abstract: Long-term memory enables language model agents to support personalized interactions, but it remains unclear when available memories warrant integration into responses.
By Lingxiang Xu, Jiaoyun Yang, Min Hu, Hongtu Chen, Ning An
Emergi-PersonaOS is a psychology‑grounded operating system designed to manage persona agents throughout their lifecycle. It structures personas into three layers—dispositional traits, characteristic adaptations, and narrative identity—allowing the system to infer current persona states from situational cues and generate appropriate actions. The OS records experiences, evaluates revision candidates, and controls belief updates through explicit review and traceable evidence, enabling controllable evolution of persona agents over long interactions.
By Haoluan Fu, Keni Chen, Xinyu Jia, Jinpeng Wang, Yuyu Yin
arXiv:2608. 07438v1 Announce Type: new Abstract: Human-like cognition does not select past experience by topical similarity alone: affective significance and unresolved conflict also shape what becomes accessible.
By Mohammad Amanlou, Parham Abed Azad, Farbod Davoodi, Mostafa Masumi, Behnam Bahrak, Abdol-Hossein Vahabie