用大模型模拟恋爱互动，先试后判匹配度。
Love First, Know Later: Persona-Based Romantic Compatibility Through LLM Text World Engines
- 用大模型做角色代理+交互环境，模拟真实恋爱过程。
- 在速配数据上预测初识化学反应，离婚数据上预测长期稳定。
- 适合想了解恋爱机制或开发智能匹配系统的人。
我们提出「爱在先，知在后」：一种计算匹配的范式革新，先模拟互动再评估兼容性。不同于对比静态资料，该框架利用大模型作为文本世界引擎，兼具角色驱动代理与交互动态建模环境双重功能。将兼容性评估形式化为奖励建模问题：根据观察到的匹配结果，学习从模拟中提取预测人类偏好的信号。核心洞察是关系成败取决于对关键时刻的回应——这一关系心理学发现被转化为数学假设，实现有效模拟。理论上证明，当大模型策略更逼近人类行为时，诱导匹配收敛至最优稳定匹配。实证上，在速配数据上验证初始化学反应预测，在离婚数据上验证长期稳定性预测。该范式支持交互式、个性化的匹配系统，用户可迭代优化其代理，开启透明、互动式兼容性评估的新可能。
原文摘要 · Abstract (English)
We propose Love First, Know Later: a paradigm shift in computational matching that simulates interactions first, then assesses compatibility. Instead of comparing static profiles, our framework leverages LLMs as text world engines that operate in dual capacity-as persona-driven agents following behavioral policies and as the environment modeling interaction dynamics. We formalize compatibility assessment as a reward-modeling problem: given observed matching outcomes, we learn to extract signals from simulations that predict human preferences. Our key insight is that relationships hinge on responses to critical moments-we translate this observation from relationship psychology into mathematical hypotheses, enabling effective simulation. Theoretically, we prove that as LLM policies better approximate human behavior, the induced matching converges to optimal stable matching. Empirically, we validate on speed dating data for initial chemistry and divorce prediction for long-term stability. This paradigm enables interactive, personalized matching systems where users iteratively refine their agents, unlocking future possibilities for transparent and interactive compatibility assessment.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。