arXiv cs.CY· Hanzhong Zhang, Muhua Huang, Jindong Wang·· 12 小时前AI 评分32
CMASE：基于生成式智能体的计算多智能体社会实验框架
Computational Multi-Agents Society Experiments: Social Modeling Framework Based on Generative Agents
AI 导读
研究者提出 CMASE，一个基于生成式智能体的框架，支持研究者以世界内角色在运行时进行可追溯的社会干预实验。CMASE 结合 LLM 驱动的感知、记忆与情绪，以及由纹理和区域地图构成的可组合环境，并复现了城市绿化与社会割裂、公共品博弈合作两项已发表实地研究，在两种差异显著的语言模型上重现了原文报告的统计模式。对照实验显示，嵌入式社会干预会留下可观察、可审计的过程记录，而参数化操控则不会。
正文 · 原文
Abstract:Computational social science has developed descriptive, interpretative, and predictive modeling, but comprehensive modeling combining in-world human intervention with outcome forecasting remains underexplored. Generative agent-based platforms scale populations or reproduce complex scenarios, but researchers typically act through setup, external controls, or post-hoc analysis rather than in-world roles. We introduce Computational Multi-Agent Society Experiments (CMASE), a generative agent-based framework for in-world researcher participation and traceable interventions at runtime. Treating simulation as a simulated ethnographic field, CMASE supports (1) real-time human-computer interaction to study intervention processes; (2) controlled experiments with ethnography-inspired observation, interviewing, and interpretation; and (3) forward exploration of intervention trajectories and downstream responses. CMASE combines LLM-driven perception, memory, and emotion; a composable environment built from texture and area maps; and researcher roles spanning observation, interviewing, participation, and intervention, so that interventions enter as social events rather than exogenous parameters. We replicate two published field studies from different disciplines: urban greenery and social fragmentation, and cooperation in a public goods game, using two substantially different language models. CMASE reproduces reported statistical patterns and provides process-level records for mechanism-oriented interpretation. A controlled comparison shows that embedded social interventions leave observable, auditable processes that parametric manipulation does not. These findings highlight CMASE's methodological value for studying interventions in small- and medium-scale social settings and its interdisciplinary potential. The official code is available at: this https URL.
| Comments: | Accepted for publication in ACM Transactions on Social Computing (TSC). 36 pages, 6 figures |
| Subjects: | Artificial Intelligence (cs.AI); Computers and Society (cs.CY); Multiagent Systems (cs.MA) |
| MSC classes: | 68T42 |
| ACM classes: | I.2.7; J.4 |
| Cite as: | arXiv:2508.17366 [cs.AI] |
| (or arXiv:2508.17366v3 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2508.17366 arXiv-issued DOI via DataCite |
Submission history
From: Hanzhong Zhang [view email]
[v1]
Sun, 24 Aug 2025 13:50:18 UTC (13,671 KB)
[v2]
Mon, 9 Mar 2026 21:16:43 UTC (1,867 KB)
[v3]
Thu, 15 Oct 2026 20:06:48 UTC (8,729 KB)
来源：arXiv cs.CY · arxiv.org