--- title: "EmoHarbor — paper by Ye et al. (2026) — summary and ideas" description: "A Chain-of-Agent design divides the simulated user into three agents: a User Thinker that infers hidden thoughts and emotional… 3 references." authors: ["Jing Ye", "Lu Xiang", "Yaping Zhang", "Chengqing Zong"] year: 2026 venue: "Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)" source: "https://aclanthology.org/2026.acl-long.53/" doi: "10.18653/v1/2026.acl-long.53" licence: "CC BY 4.0 (ACL Anthology)" licence_url: "https://creativecommons.org/licenses/by/4.0/" summary_licence: "Elamur Cosmic License" canonical: "https://research.elamur.ai/free/en/papers/ye-2026-emoharbor-evaluating-personalized-emotional-support/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/ye-2026-emoharbor-evaluating-personalized-emotional-support/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/31/) / EmoHarbor: Evaluating Personalized Emotional Support by Simulating the User's Internal World # EmoHarbor: Evaluating Personalized Emotional Support by Simulating the User's Internal World **Authors:** [Jing Ye](https://md.research.elamur.ai/free/en/authors/jing-ye/), [Lu Xiang](https://md.research.elamur.ai/free/en/authors/lu-xiang/), [Yaping Zhang](https://md.research.elamur.ai/free/en/authors/yaping-zhang/) and [Chengqing Zong](https://md.research.elamur.ai/free/en/authors/chengqing-zong/) · **Year:** 2026 · **Venue:** [Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)](https://md.research.elamur.ai/free/en/venues/acl/) ([ACL 2026](https://md.research.elamur.ai/free/en/venues/acl/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/) **Links:** [Publisher's page](https://aclanthology.org/2026.acl-long.53/) · [PDF](https://aclanthology.org/2026.acl-long.53.pdf) · [DOI 10.18653/v1/2026.acl-long.53](https://doi.org/10.18653/v1/2026.acl-long.53) · [OpenAlex](https://openalex.org/W7166881377) **Citations:** 0 citations (OpenAlex, 2026-10-14) ## Summary Most automatic evaluations of emotional support conversations (ESC) take an outside "expert" view. They tend to give high scores to generically empathetic replies without checking whether the help suits a particular person. EmoHarbor changes this with a User-as-a-Judge approach: an agent simulates the seeker's internal world and rates the supporter from that user's perspective. A Chain-of-Agent design divides the simulated user into three agents: - a User Thinker that infers hidden thoughts and emotional reactions, - a User Talker that produces replies consistent with the user's personality, - a User Evaluator that scores the supporter as the conversation unfolds. The benchmark uses 100 profiles. Seeds came from real questionnaire responses and were then expanded with LLMs. Responses are judged on 10 dimensions of personalized support quality. The authors tested 20 advanced LLMs. These models handle broad empathy well but repeatedly fail to adapt support to the individual user. The authors also report strong agreement with human judgments. This matters because it suggests ESC research should aim for user-aware support rather than simply more empathetic wording. ## Key points - Each user profile has four parts: demographic attributes, preference-related attributes (Big-Five, MBTI, habits, speech style), counseling-related attributes (problem, emotion, goals, relations) and a scenario script. - The 100 profiles span ages from adolescence to senior adulthood, 28 occupations, all 16 MBTI types and 16 counseling scenario types, such as workplace stress and life transitions. - During simulation, the supporter sees only the visible dialogue turns. The simulated user keeps a separate memory that also stores its latent internal states. - In a turn-by-turn analysis of Doubao-Pro, every metric drifts slightly downward over longer dialogues. Redundancy degrades most sharply, indicating increasingly repetitive replies. - The authors list three limitations: simulated users follow predefined structures, human-agreement studies may carry biases, and multi-turn simulation is computationally costly. Code is released at github.com/kaedeharakazuha678/EmoHarbor-25. *Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.* ## Institutions - [Chinese Academy of Sciences](https://md.research.elamur.ai/free/en/government/chinese-academy-of-sciences/) — Government body, Beijing, China · 246 works · 24,951 citations - [Institute of Automation](https://md.research.elamur.ai/free/en/labs/institute-of-automation/) — Research institute, Beijing, China · 87 works · 14,883 citations - [University of Chinese Academy of Sciences](https://md.research.elamur.ai/free/en/universities/university-of-chinese-academy-of-sciences/) — University, Beijing, China · 188 works · 8,743 citations 📚 Shelves (7): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works · [💭 Psychology](https://md.research.elamur.ai/free/en/shelves/psychology/) · 1,649 works · [💭 Experimental and Cognitive Psychology](https://md.research.elamur.ai/free/en/shelves/psychology/experimental-and-cognitive-psychology/) · 930 works · [💭 Social Psychology](https://md.research.elamur.ai/free/en/shelves/psychology/social-psychology/) · 330 works 🧭 Topics (1): [😊 Sentiment & emotion](https://md.research.elamur.ai/free/en/topics/sentiment-emotion/) · 1,035 works ## Cite Cite as: Jing Ye, Lu Xiang, Yaping Zhang and Chengqing Zong. 2026. EmoHarbor: Evaluating Personalized Emotional Support by Simulating the User's Internal World. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @inproceedings{ye2026emoharbor, title = {{EmoHarbor: Evaluating Personalized Emotional Support by Simulating the User's Internal World}}, author = {Jing Ye, Lu Xiang, Yaping Zhang and Chengqing Zong}, booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)}, year = {2026}, doi = {10.18653/v1/2026.acl-long.53}, url = {https://doi.org/10.18653/v1/2026.acl-long.53} } ``` - [← previous EmoAra: Emotion-Preserving English Speech Transcription and Cross-Lingual Translation with Arabic Text-to-Speech](https://md.research.elamur.ai/free/en/papers/hassan-2026-emoara-emotion-preserving-english-speech/) - [next → Emoji Reactions on Telegram: Unreliable Indicators of Emotional Resonance](https://md.research.elamur.ai/free/en/papers/tardelli-2026-emoji-reactions-telegram-unreliable-indicators/) - [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/31/) ## References 3 references, 1 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, and 1 others. 2023. [Gpt-4 technical report](https://md.research.elamur.ai/free/en/papers/openai-2023-gpt-4-technical-report/). arXiv preprint arXiv:2303.08774. 2. Anthropic. 2024. Claude 3.5 sonnet. [find](https://scholar.google.com/scholar?q=Anthropic%2E+2024%2E+Claude+3%2E5+sonnet%2E) 3. Anthropic. 2025. Introducing claude 4. \#\# Ethical Considerations ByteDance. 2024. Doubao. [find](https://scholar.google.com/scholar?q=Anthropic%2E+2025%2E+Introducing+claude+4%2E+%5C%23%5C%23+Ethical+Considerations+ByteDance%2E+2024%2E+Doubao%2E) *Updated 2 November 2026*