cs.AIMar 21, 2026

AI-Driven Multi-Agent Simulation of Stratified Polyamory Systems: A Computational Framework for Optimizing Social Reproductive Efficiency

Authors: Yicai Xing

Organizations: Independent Researcher

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

Contemporary societies face a severe crisis of demographic reproduction. Global fertility rates continue to decline precipitously, with East Asian nations exhibiting the most dramatic trends -- China's total fertility rate (TFR) fell to approximately 1.0 in 2023, while South Korea's dropped below 0.72. Simultaneously, the institution of marriage is undergoing structural disintegration: educated women rationally reject unions lacking both emotional fulfillment and economic security, while a growing proportion of men at the lower end of the socioeconomic spectrum experience chronic sexual deprivation, anxiety, and learned helplessness. This paper proposes a computational framework for modeling and evaluating a Stratified Polyamory System (SPS) using techniques from agent-based modeling (ABM), multi-agent reinforcement learning (MARL), and large language model (LLM)-empowered social simulation. The SPS permits individuals to maintain a limited number of legally recognized secondary partners in addition to one primary spouse, combined with socialized child-rearing and inheritance reform. We formalize the A/B/C stratification as heterogeneous agent types in a multi-agent system and model the matching process as a MARL problem amenable to Proximal Policy Optimization (PPO). The mating network is analyzed using graph neural network (GNN) representations. Drawing on evolutionary psychology, behavioral ecology, social stratification theory, computational social science, algorithmic fairness, and institutional economics, we argue that SPS can improve aggregate social welfare in the Pareto sense. Preliminary computational results demonstrate the framework's viability in addressing the dual crisis of female motherhood penalties and male sexlessness, while offering a non-violent mechanism for wealth dispersion analogous to the historical Chinese Grace Decree (Tui'en Ling).

Figures & tables

Figure 1: Long-term decline in total fertility rates (TFR) across major East Asian nations. Data: UN Population Division [ 1 ] , national statistical bureaus, Choe & Lee [ 2 ] .
Figure 2: The dual dimensions of monogamy’s structural failure and their convergent effect on social reproduction. Each dimension is supported by key empirical literature.
Figure 3: Distribution of mating systems among mammals. Based on phylogenetic analysis by Lukas & Clutton-Brock [ 53 ] . Strict monogamy accounts for only ∼\sim 9% of species.
Figure 4: The three-channel biological model of love. Visual [ 64 , 76 ] , olfactory [ 77 , 78 ] , and behavioral [ 79 , 80 ] channels jointly constitute the genetic quality assessment system.
TierComposite TraitsTypical ProfileUnder Monogamy
AResource-rich, physically/intellectually outstandingElite professionals, entrepreneurs, high-attractiveness individualsMulti-dimensional needs constrained by single partner
BAverage composite attractivenessSocial majorityPartial preference for A-tier unattainable; limited satisfaction
CEconomically deprived, disadvantaged in appearance/social skillsLow-income, socially isolatedSome permanently unpartnered; welfare ≈\approx 0; instability risk [ 48 ]
Table 1: A/B/C Tier Model Overview (analytical tool, not institutional label)
Figure 5: SPS institutional structure and rights system. The limited rights design for companions avoids equating secondary relationships with marriage while safeguarding children’s interests. Legal frameworks for multi-partner recognition are emerging [ 82 ] .
Figure 6: Cross-tier partner network under SPS. Tier B’s multi-directional compatibility renders it the system’s buffer and connector layer, ensuring cross-tier flow of sexual and emotional resources. This model accords with Orians’ (1969) Polygyny Threshold Model [ 83 ] and Emlen & Oring’s (1977) ecological framework [ 16 ] .
Figure 7: Intergenerational wealth dispersion comparison via the Grace Decree effect. SPS accelerates wealth dispersal by increasing the number of legitimate heirs of high-resource individuals.
Figure 8: Pareto improvement argument. Under SPS, expected welfare improves across all tiers, with the most significant gains at Tier C. Values derived from theoretical model projections.
Figure 9: Four independent pathways through which SPS promotes fertility recovery. Each pathway is supported by empirical literature.
CriticismArgumentResponse & Supporting Literature
Objectification of womenMultiple partners commodifies womenSPS is strictly gender-symmetric. Women hold identical polyamorous rights. Orians’ (1969) model [ 83 ] suggests polygamy may be advantageous for women under resource inequality
Inevitable jealousyPolyamory necessarily produces jealousyConley et al. (2013) [ 25 ] : CNM relationships exhibit lower jealousy than infidelity within monogamy. Moors et al. (2017) [ 26 ] : polyamorous relationship satisfaction is comparable to monogamous relationships. Rubel & Bogaert (2015) [ 27 ] : CNM correlates with positive psychological well-being. Sheff (2014) [ 28 ] : ethnographic evidence of successful poly families
ABC is discriminatoryTiering people is dehumanizingA/B/C is a descriptive analytical tool (analogous to income quintiles in economics), not a basis for differential legal treatment. All individuals enjoy identical institutional rights. Becker’s (1973) [ 17 ] marriage market model already incorporates hierarchical structure
Undermines familyWeakened families harm childrenKibbutz research [ 87 ] : socialized child-rearing produces normal developmental outcomes. Golombok (2016) [ 89 ] : children in non-traditional families show no significant psychological developmental differences
ImpracticalCannot be implemented nowDirectional framework requiring gradual implementation. See Section 9 . Emerging legal recognition of polyamorous partnerships [ 82 ] suggests institutional pathways are opening
Table 2: Principal criticisms of SPS and evidence-based responses
Figure 10: Graduated implementation roadmap for SPS. Each phase builds upon the institutional foundations and social consensus established by its predecessor. Emerging legal recognition of polyamorous partnerships [ 82 ] suggests that Phase I is already partially underway in some jurisdictions.
ParameterValue
Population size NN10,000 agents
Gender ratio50:50
Tier distribution (A:B:C)15:60:25
Simulation horizon100 years (time steps)
Partner limit (SPS)3 (1 spouse + 2 companions)
Partner limit (monogamy baseline)1
Table 3: Proposed simulation parameters

Explore similar work

CardsList
Sep 28, 2026

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

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---whom do I like? and 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 50×5050\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.

Wangxuan Fan, Xiaoyu Nie, Zhoutian Shi +5

The Chinese University of Hong Kong, Shenzhen

Agent-Based ModelingLarge Language Model-Based Social Simulation
AskPDF
Jul 7, 2026

From Blueprint to Reality: Modeling and Applying Putnam's Social Capital Theory with LLM-based Multi-agent Simulations

Putnam's Social Capital Theory is a foundational framework for collective action and community prosperity. However, traditional empirical methods face practical limits on control and replication. Meanwhile, LLM-based social simulations are typically behavior-driven and lack theory-aligned environments for modeling Putnam's core propositions. To address these gaps, we introduce SocaSim, an LLM-based multi-agent simulation framework to study Putnam's Social Capital Theory from theoretical blueprint to simulated reality. Specifically, we build an environment integrating social network evolution, trust dynamics, and norm propagation, where agents engage in repeated collective-action experiments, and then apply the three dimensions to analyze adaptation challenges in smart elderly care. Our simulations reproduce Putnam's macro-level patterns and exhibit strong human-agent alignment at the group level. Unlike traditional methods, SocaSim traces micro-level causal pathways of social network, trust, and norms via round-by-round simulations and counterfactual interventions, enabling process-level interpretability. Taken together, these capabilities establish a research paradigm that leverages LLM agents to bridge social science and computer science.

Shiyi Ling, Zhi Zheng, Hui Zheng +3

State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China · Anhui University · North Automatic Control Technology Institute +1

Multi-Agent LLM SystemsHuman Behavior SimulationAgent-Based Modeling
AskPDF
Aug 4, 2026

Learning Sexism Detection Using Multi-Agent Perspectivist Preference Optimization

When people label text for sexism, they often disagree, and not because some of them are wrong: they genuinely perceive sexism differently. Most NLP systems discard this disagreement by collapsing it into a majority vote. We propose the Multi-Agent Perspectivist Preference Optimization (MAP-PO) framework to keep these different perspectives. On the EXIST 2024 dataset of labeled English and Spanish tweets, we first cluster annotators by their labeling behavior rather than their demographic attributes. We then fine-tune one Large Language Model agent per cluster to reproduce that cluster's annotation behavior, and coordinate the agents with preference optimization that combines individual and team-level rewards. We evaluate MAP-PO in four settings defined by two languages and two backbone language models, asking whether each agent reproduces the annotations of its own cluster and whether the agents together reproduce the majority label. Two findings hold in all four settings. First, without fine-tuning the agents behave almost identically, so cluster-specific training is necessary. Second, we show that training each agent only on the labels of its own cluster pushes the agents far beyond the clusters they should represent, while adding a shared team-level training signal consistently keeps each agent calibrated to its cluster.

Hadi Mohammadi, Tina Shahedi, Robert A. Bagheri +2

Department of Methodology and Statistics, Utrecht University, The Netherlands · Department of Information and Computing Sciences, Utrecht University, The Netherlands · Field Technology Innovations (FTI) & Robotics, Wageningen University & Research, The Netherlands

Annotator DisagreementPreference OptimizationMulti-Agent LLMsPreference Learning
AskPDF