Saved in:
Bibliographic Details
Main Authors: Yue, Matthew, Xu, Zhikun, Gupta, Vivek, Ha, Thao, Sharabi, Liesal, Zhou, Ben
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.00414
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912620709150720
author Yue, Matthew
Xu, Zhikun
Gupta, Vivek
Ha, Thao
Sharabi, Liesal
Zhou, Ben
author_facet Yue, Matthew
Xu, Zhikun
Gupta, Vivek
Ha, Thao
Sharabi, Liesal
Zhou, Ben
contents Most dating technologies optimize for getting together, not staying together. We present RELATE-Sim, a theory-grounded simulator that models how couples behave at consequential turning points-exclusivity talks, conflict-and-repair episodes, relocations-rather than static traits. Two persona-aligned LLM agents (one per partner) interact under a centralized Scene Master that frames each turning point as a compact set of realistic options, advances the narrative, and infers interpretable state changes and an auditable commitment estimate after each scene. On a longitudinal dataset of 71 couples with two-year follow-ups, simulation-aware predictions outperform a personas-only baseline while surfacing actionable markers (e.g., repair attempts acknowledged, clarity shifts) that explain why trajectories diverge. RELATE-Sim pushes the relationship research's focus from matchmaking to maintenance, providing a transparent, extensible platform for understanding and forecasting long-term relationship dynamics.
format Preprint
id arxiv_https___arxiv_org_abs_2510_00414
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle RELATE-Sim: Leveraging Turning Point Theory and LLM Agents to Predict and Understand Long-Term Relationship Dynamics through Interactive Narrative Simulations
Yue, Matthew
Xu, Zhikun
Gupta, Vivek
Ha, Thao
Sharabi, Liesal
Zhou, Ben
Human-Computer Interaction
Most dating technologies optimize for getting together, not staying together. We present RELATE-Sim, a theory-grounded simulator that models how couples behave at consequential turning points-exclusivity talks, conflict-and-repair episodes, relocations-rather than static traits. Two persona-aligned LLM agents (one per partner) interact under a centralized Scene Master that frames each turning point as a compact set of realistic options, advances the narrative, and infers interpretable state changes and an auditable commitment estimate after each scene. On a longitudinal dataset of 71 couples with two-year follow-ups, simulation-aware predictions outperform a personas-only baseline while surfacing actionable markers (e.g., repair attempts acknowledged, clarity shifts) that explain why trajectories diverge. RELATE-Sim pushes the relationship research's focus from matchmaking to maintenance, providing a transparent, extensible platform for understanding and forecasting long-term relationship dynamics.
title RELATE-Sim: Leveraging Turning Point Theory and LLM Agents to Predict and Understand Long-Term Relationship Dynamics through Interactive Narrative Simulations
topic Human-Computer Interaction
url https://arxiv.org/abs/2510.00414