Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2510.06225 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914080124567552 |
|---|---|
| author | Li, Gang Lin, Jie Tang, Yining Wang, Ziteng Huang, Yirui Zhang, Junyu Luo, Shuang Wu, Chao Guo, Yike |
| author_facet | Li, Gang Lin, Jie Tang, Yining Wang, Ziteng Huang, Yirui Zhang, Junyu Luo, Shuang Wu, Chao Guo, Yike |
| contents | Multi-agent social interaction has clearly benefited from Large Language Models. However, current simulation systems still face challenges such as difficulties in scaling to diverse scenarios and poor reusability due to a lack of modular design. To address these issues, we designed and developed a modular, object-oriented framework that organically integrates various base classes through a hierarchical structure, harvesting scalability and reusability. We inherited the framework to realize common derived classes. Additionally, a memory summarization mechanism is proposed to filter and distill relevant information from raw memory data, prioritizing contextually salient events and interactions. By selecting and combining some necessary derived classes, we customized a specific simulated environment. Utilizing this simulated environment, we successfully simulated human interactions on social media, replicating real-world online social behaviors. The source code for the project will be released and evolve. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_06225 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Generalized Multi-agent Social Simulation Framework Li, Gang Lin, Jie Tang, Yining Wang, Ziteng Huang, Yirui Zhang, Junyu Luo, Shuang Wu, Chao Guo, Yike Physics and Society Artificial Intelligence Multi-agent social interaction has clearly benefited from Large Language Models. However, current simulation systems still face challenges such as difficulties in scaling to diverse scenarios and poor reusability due to a lack of modular design. To address these issues, we designed and developed a modular, object-oriented framework that organically integrates various base classes through a hierarchical structure, harvesting scalability and reusability. We inherited the framework to realize common derived classes. Additionally, a memory summarization mechanism is proposed to filter and distill relevant information from raw memory data, prioritizing contextually salient events and interactions. By selecting and combining some necessary derived classes, we customized a specific simulated environment. Utilizing this simulated environment, we successfully simulated human interactions on social media, replicating real-world online social behaviors. The source code for the project will be released and evolve. |
| title | Generalized Multi-agent Social Simulation Framework |
| topic | Physics and Society Artificial Intelligence |
| url | https://arxiv.org/abs/2510.06225 |