# Love First, Know Later: Persona-Based Romantic Compatibility Through LLM Text World Engines

arXiv: https://arxiv.org/abs/2512.11844 · HTML: https://mlsanity.com/paper/2512.11844/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 31 references that are in the map.
- First posted on arXiv 4 Dec 2025.

## Builds on (most cited first, 21 of 21)

- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents](https://mlsanity.com/paper/2310.11667/) (2023)
- [Evaluating Large Language Models in Theory of Mind Tasks](https://mlsanity.com/paper/2302.02083/) (2023)
- [InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviews](https://mlsanity.com/paper/2310.17976/) (2023)
- [OASIS: Open Agent Social Interaction Simulations with One Million Agents](https://mlsanity.com/paper/2411.11581/) (2024)
- [Group Robust Preference Optimization in Reward-free RLHF](https://mlsanity.com/paper/2405.20304/) (2024)
- [Training Socially Aligned Language Models on Simulated Social Interactions](https://mlsanity.com/paper/2305.16960/) (2023)
- [BIG5-CHAT: Shaping LLM Personalities Through Training on Human-Grounded Data](https://mlsanity.com/paper/2410.16491/) (2024)
- [Exploring Prosocial Irrationality for LLM Agents: A Social Cognition View](https://mlsanity.com/paper/2405.14744/) (2024)
- [LLMs generate structurally realistic social networks but overestimate political homophily](https://mlsanity.com/paper/2408.16629/) (2024)
- [Enhancing Persona Consistency for LLMs' Role-Playing using Persona-Aware Contrastive Learning](https://mlsanity.com/paper/2503.17662/) (2025)
- [Diverse Preference Learning for Capabilities and Alignment](https://mlsanity.com/paper/2511.08594/) (2025)
- [Synthetic Socratic Debates: Examining Persona Effects on Moral Decision and Persuasion Dynamics](https://mlsanity.com/paper/2506.12657/) (2025)
- [PRODIGy: a PROfile-based DIalogue Generation dataset](https://mlsanity.com/paper/2311.05195/) (2023)
- [Earlier Tokens Contribute More: Learning Direct Preference Optimization From Temporal Decay Perspective](https://mlsanity.com/paper/2502.14340/) (2025)
- [Humanizing Machines: Rethinking LLM Anthropomorphism Through a Multi-Level Framework of Design](https://mlsanity.com/paper/2508.17573/) (2025)
- [Neural Active Learning Beyond Bandits](https://mlsanity.com/paper/2404.12522/) (2024)
- [United Minds or Isolated Agents? Exploring Coordination of LLMs under Cognitive Load Theory](https://mlsanity.com/paper/2506.06843/) (2025)
- [CoBRA: Programming Cognitive Bias in Social Agents Using Classic Social Science Experiments](https://mlsanity.com/paper/2509.13588/) (2025)

## Built on by (most cited first, 3 of 3)

- [RedFlow: Redirect Failure into Action-Level Corrections for Flow-matching VLA Policy](https://mlsanity.com/paper/2607.27782/) (2026)
- [EMFormer: Efficient Multi-Scale Transformer for Accumulative Context Weather Forecasting](https://mlsanity.com/paper/2602.01194/) (2026)
- [From Preference to Reciprocity: Decentralized Matching with Empirically Grounded LLM-agent Based Modeling](https://mlsanity.com/paper/2609.34679/) (2026)

## Abstract (arXiv)

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.