RELATE-Sim: Leveraging Turning Point Theory and LLM Agents to Predict and Understand Long-Term Relationship Dynamics through Interactive Narrative Simulations

2025-09-30

AI Summary

Traditional dating technologies focus on initial matching, neglecting the dynamic evolution of long-term intimate relationships—particularly at critical junctures (e.g., exclusivity establishment, conflict resolution, relocation) where relational trajectories become highly unpredictable. Method: We propose an interpretable simulation framework grounded in turning-point theory, featuring a dual-role LLM agent system coordinated by a central scenario controller. The architecture integrates contextualized control, narrative progression, and state inference modules, calibrated via longitudinal partner data to enable simulation-aware prediction. Contribution/Results: Evaluated on two-year follow-up data from 71 couples, our approach significantly outperforms static personality–based baselines. It identifies actionable dynamic markers—including repair attempts and shifts in cognitive clarity—and supports audit-style assessment of long-term commitment levels. This work advances relationship science from a “matching” paradigm toward mechanistic understanding of relationship maintenance.

Technology Category

• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Multiagent Systems: Agent-Based Simulation and Emergent Behavior
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Studies of user behavior, including longitudinal effects of personalized systems
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

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.

Problem

• Predict long-term relationship dynamics through interactive simulations
• Model couple behavior at consequential relationship turning points
• Shift relationship research focus from matchmaking to maintenance

Innovation

• Simulates couples' behavior at relationship turning points
• Uses LLM agents with centralized Scene Master control
• Predicts relationship dynamics through interactive narrative simulations