Rethinking Social Simulation in Open-Population Systems: From Persistent Agents to Communication Processes
Abstract
Large language models (LLMs) have enabled social simulation with persistent agents, where fixed computational individuals maintain internal states and interact over time. However, large-scale social networks are inherently open-population systems: the participating population changes over time, users enter and leave dynamically, and only a sparse subset becomes observable through communication at any given time. In such systems, persistent account identities do not provide continuously observable individual-state trajectories, making recursively maintained psychological states insufficiently grounded in empirical observations. We therefore shift the simulation target from persistent individual trajectories to the observable evolution of social communication, modeling who participates, what they communicate, and how these communications shape subsequent system dynamics. We instantiate this formulation with participant activation from a global user pool, collective state transition, and an LLM policy for communication generation, while explicitly separating environmental inputs from endogenous system evolution. Across five Qwen backbones, our framework reduces average KL divergence by 71.2% over Direct LLM and 35.0% over MF-LLM, with boundary and counterfactual experiments further validating the proposed modeling boundaries. Our results support communication-centered simulation as a principled formulation for long-horizon open-population social systems. Project Website: https://ai4ss.github.io/OpenSim/
Related
- Direct Neutrino Communication Through the Earth: NuMI-Calibrated Simulation and Far-Field Sensitivity
- Tame the Umklapp Processes in Real-Time Lattice Simulation for Hydrodynamics: An Ising Field Theory Study
- Finite Element Simulation of Microwave Technologies for PowderBased Volumetric Additive Manufacturing Processes
- Persistent level-resolved transmon population after dispersive readout, and the limits of its open-system description
- Rethinking free-space orbital angular momentum quantum key distribution: encoding selection and branch-cut-length-minimized adaptive optics
BibTeX
@misc{zhang2026rethinking,
title = {{Rethinking Social Simulation in Open-Population Systems: From Persistent Agents to Communication Processes}},
author = {Yunyao Zhang and Yihao Ai and Boqi Xu and Zuocheng Ying and Junqing Yu and Zikai Song},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.37687},
eprint = {2610.37687},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.37687},
}
RIS
TY - UNPB
TI - Rethinking Social Simulation in Open-Population Systems: From Persistent Agents to Communication Processes
AU - Yunyao Zhang
AU - Yihao Ai
AU - Boqi Xu
AU - Zuocheng Ying
AU - Junqing Yu
AU - Zikai Song
PY - 2026
DA - 2026/10/17
PB - arXiv
DO - 10.48550/arxiv.2610.37687
UR - https://arxiv.org/abs/2610.37687
AB - Large language models (LLMs) have enabled social simulation with persistent agents, where fixed computational individuals maintain internal states and interact over time. However, large-scale social networks are inherently open-population systems: the participating population changes over time, users enter and leave dynamically, and only a sparse subset becomes observable through communication at any given time. In such systems, persistent account identities do not provide continuously observable individual-state trajectories, making recursively maintained psychological states insufficiently grounded in empirical observations. We therefore shift the simulation target from persistent individual trajectories to the observable evolution of social communication, modeling who participates, what they communicate, and how these communications shape subsequent system dynamics. We instantiate this formulation with participant activation from a global user pool, collective state transition, and an LLM policy for communication generation, while explicitly separating environmental inputs from endogenous system evolution. Across five Qwen backbones, our framework reduces average KL divergence by 71.2% over Direct LLM and 35.0% over MF-LLM, with boundary and counterfactual experiments further validating the proposed modeling boundaries. Our results support communication-centered simulation as a principled formulation for long-horizon open-population social systems. Project Website: https://ai4ss.github.io/OpenSim/
ER -