Saved in:
Bibliographic Details
Main Authors: Zhou, Xuan, Sun, Yanhui, Yao, Hantao, He, Allen, Zhang, Yongdong, Liu, Wu
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.07692
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915992637014016
author Zhou, Xuan
Sun, Yanhui
Yao, Hantao
He, Allen
Zhang, Yongdong
Liu, Wu
author_facet Zhou, Xuan
Sun, Yanhui
Yao, Hantao
He, Allen
Zhang, Yongdong
Liu, Wu
contents Large-scale social simulators are essential for studying complex social patterns. Prior work explores hybrid methods to scale up simulations, combining large language models (LLM)-based agents with numerical agent-based models (ABM). However, this incurs high latency due to expensive memory retrieval and sequential ABM execution. To address this challenge, we propose GASim, a graph-accelerated hybrid multi-agent framework for large-scale social simulations. For core agents driven by LLM, GASim introduces Graph-Optimized Memory (GOM) to replace intensive LLM-based retrieval pipelines with lightweight propagation over a sparse memory graph. For the majority of ordinary agents, GASim employs Graph Message Passing (GMP), substituting sequential ABM execution with parallel updates by fine-grained feature aggregation and Graph Attention Network. We further introduce Entropy-Driven Grouping (EDG) that coordinates this hybrid partitioning, leveraging information entropy to dynamically identify emergent core agents situated in information-diverse neighborhoods. Extensive experiments show that GASim not only delivers a substantial 9.94-fold end-to-end speedup over the traditional hybrid framework but also consumes less than 20% of baseline tokens, significantly reducing costs while preserving strong alignment with real-world public opinion trends. Our code is available at https://github.com/Jasmine0201/GASim.
format Preprint
id arxiv_https___arxiv_org_abs_2605_07692
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle GASim: A Graph-Accelerated Hybrid Framework for Social Simulation
Zhou, Xuan
Sun, Yanhui
Yao, Hantao
He, Allen
Zhang, Yongdong
Liu, Wu
Artificial Intelligence
Large-scale social simulators are essential for studying complex social patterns. Prior work explores hybrid methods to scale up simulations, combining large language models (LLM)-based agents with numerical agent-based models (ABM). However, this incurs high latency due to expensive memory retrieval and sequential ABM execution. To address this challenge, we propose GASim, a graph-accelerated hybrid multi-agent framework for large-scale social simulations. For core agents driven by LLM, GASim introduces Graph-Optimized Memory (GOM) to replace intensive LLM-based retrieval pipelines with lightweight propagation over a sparse memory graph. For the majority of ordinary agents, GASim employs Graph Message Passing (GMP), substituting sequential ABM execution with parallel updates by fine-grained feature aggregation and Graph Attention Network. We further introduce Entropy-Driven Grouping (EDG) that coordinates this hybrid partitioning, leveraging information entropy to dynamically identify emergent core agents situated in information-diverse neighborhoods. Extensive experiments show that GASim not only delivers a substantial 9.94-fold end-to-end speedup over the traditional hybrid framework but also consumes less than 20% of baseline tokens, significantly reducing costs while preserving strong alignment with real-world public opinion trends. Our code is available at https://github.com/Jasmine0201/GASim.
title GASim: A Graph-Accelerated Hybrid Framework for Social Simulation
topic Artificial Intelligence
url https://arxiv.org/abs/2605.07692