Papers for

online dating platforms

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

One woman’s strategy changes partner rankings in stable marriage markets

One Strategic Woman: Sharp Ranks and a Persistent Core

Abstract: In a balanced random stable-marriage market, one fixed woman manipulates men-proposing deferred acceptance to obtain her best attainable partner. We prove that the women's expected average true partner rank is asymptotic to $(\ln n)^2$, improving the previous $O((\ln n)^4)$ bound, while the men's is asymptotic to $n/(2\ln n)$. The men's and women's average ranks, normalized by $n/\ln n$ and $\ln n$, converge jointly in distribution to $(U,U^{-1})$, where $U$ is uniform on $(0,1)$. Under optimal truthful truncation, the span of women's average ranks within the reported stable core, divided by $\ln n$, converges in distribution to $U^{-1}-1$.

Wed 4 NovComputer Science and Game Theory
The gist
The paper studies a situation where many men and women are matched as partners, like in dating or job assignments. It looks at what happens when one woman strategically changes her preferences to get her best possible partner. The authors show math formulas describing how good partners the men and women get on average with this strategy. They also explain how much women’s choices can vary when they report their preferences truthfully in this matching game.
Open → 2611.06175v1

Decentralized matching improves outcomes with AI agents in simulated markets

From Preference to Reciprocity: Decentralized Matching with Empirically Grounded LLM-agent Based Modeling

Abstract: Bipartite matching is a fundamental problem in game theory and market design. Classical approaches such as Gale--Shapley assume complete preferences and centralized computation, whereas many real-world matching processes are decentralized, asynchronous, and shaped by sequential interaction under limited information. We propose a dynamic bipartite matching framework that combines large language model (LLM) agents with contextual bandits. In a simulated Chinese marriage market, economically grounded LLM agents evaluate locally encountered candidates, while agent-specific Logistic-UCB models learn reciprocal acceptance from realized proposal outcomes. The mechanism therefore separates two decisions---\emph{whom do I like?} and \emph{who is likely to like me back?}---without requiring ex ante market-wide preference rankings. We first validate LLM-induced mate preferences against the empirical conditional-logit reference across multiple LLM backbones. In the $50\times50$ matching experiment, Bandit-UCB achieves the highest mean mutual welfare (56.01 versus 54.87 for Gale--Shapley), a smaller gender rank gap than the classical baselines, and the fewest blocking pairs among the LLM-ABM policies. Learned acceptance models show economically interpretable gender-differentiated associations, while counterfactual setups reveal no systematic unilateral advantage from prior search knowledge. Overall, these results support the advantages of decentralized matching with LLM-based behavioral modeling and online learning under incomplete information for economic simulation and computational social science research.

Mon 28 SeptMachine LearningArtificial Intelligence
The gist
People often try to pair up in markets like dating or jobs, but usually, they need to know everyone's full preferences and use a central system to match them. This paper shows a new way where computer agents powered by large language models (LLMs) learn who they like and who likes them back on their own without needing complete knowledge upfront. The agents interact and learn in a simulated marriage market to find matches, performing better than the traditional Gale-Shapley method in some key ways. This approach better models how real decentralized matching happens when people have limited info and act sequentially.
Open → 2609.34679v1