Salvato in:
Dettagli Bibliografici
Autori principali: Zhang, Yunyao, Ai, Yihao, Ying, Zuocheng, Mi, Qirui, Yu, Junqing, Yang, Wei, Song, Zikai
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2604.05516
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911575749689344
author Zhang, Yunyao
Ai, Yihao
Ying, Zuocheng
Mi, Qirui
Yu, Junqing
Yang, Wei
Song, Zikai
author_facet Zhang, Yunyao
Ai, Yihao
Ying, Zuocheng
Mi, Qirui
Yu, Junqing
Yang, Wei
Song, Zikai
contents Social network simulation aims to model collective opinion dynamics in large populations, but existing LLM-based simulators mainly focus on aggregate dynamics while largely ignoring individual internal states. This limits their ability to capture opinion reversals driven by gradual individual shifts and makes them unreliable in long-horizon simulations. We propose MF-MDP, a social simulation framework that tightly couples macro-level collective dynamics with micro-level individual states. MF-MDP explicitly models per-agent latent opinion states with a state transition mechanism, combining individual Markov Decision Processes at the micro level with a mean-field collective framework at the macro level. This allows individual behaviors to change internal states gradually rather than trigger instant reactions, enabling the simulator to distinguish agents that are close to switching from those that are far from switching, capture opinion reversals, and maintain accuracy over long horizons. Across real-world events, MF-MDP supports stable simulation of long-horizon social processes with up to 40,000 interactions, compared with about 300 in the baseline MF-LLM, while reducing long-horizon KL divergence by 75.3% (1.2490 to 0.3089) and reversal KL by 66.9% (1.6425 to 0.5434), significantly mitigating the drift observed in MF-LLM. Code is available at github.com/AI4SS/MF-MDP.
format Preprint
id arxiv_https___arxiv_org_abs_2604_05516
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Coupling Macro Dynamics and Micro States for Long-Horizon Social Simulation
Zhang, Yunyao
Ai, Yihao
Ying, Zuocheng
Mi, Qirui
Yu, Junqing
Yang, Wei
Song, Zikai
Social and Information Networks
Social network simulation aims to model collective opinion dynamics in large populations, but existing LLM-based simulators mainly focus on aggregate dynamics while largely ignoring individual internal states. This limits their ability to capture opinion reversals driven by gradual individual shifts and makes them unreliable in long-horizon simulations. We propose MF-MDP, a social simulation framework that tightly couples macro-level collective dynamics with micro-level individual states. MF-MDP explicitly models per-agent latent opinion states with a state transition mechanism, combining individual Markov Decision Processes at the micro level with a mean-field collective framework at the macro level. This allows individual behaviors to change internal states gradually rather than trigger instant reactions, enabling the simulator to distinguish agents that are close to switching from those that are far from switching, capture opinion reversals, and maintain accuracy over long horizons. Across real-world events, MF-MDP supports stable simulation of long-horizon social processes with up to 40,000 interactions, compared with about 300 in the baseline MF-LLM, while reducing long-horizon KL divergence by 75.3% (1.2490 to 0.3089) and reversal KL by 66.9% (1.6425 to 0.5434), significantly mitigating the drift observed in MF-LLM. Code is available at github.com/AI4SS/MF-MDP.
title Coupling Macro Dynamics and Micro States for Long-Horizon Social Simulation
topic Social and Information Networks
url https://arxiv.org/abs/2604.05516