GASim: A Graph-Accelerated Hybrid Framework for Social Simulation
About
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.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Long-term Conversational Memory Retrieval | LoCoMo 2024 | Single Hop Accuracy75.39 | 6 | |
| Trend Alignment | Business | Delta Bias0.0807 | 6 | |
| Trend Alignment | Education | ∆Bias0.0716 | 6 | |
| Trend Alignment | Politics | ∆Bias0.07 | 6 | |
| Opinion Simulation | Social Media Opinion 10,000 agents | Core Simulation Time19.3 | 2 |