跳到正文
arXiv cs.AI· Shaobin He, Yan Gao, Quan Zheng, Zhenyang Lin, Zhen Liu, Jiyan He, Shuxin Zheng·· 1 小时前AI 评分45

ABSClaw:从虚构世界到基于真实数据的社会模拟

ABSClaw: From Invented Worlds to Reality-Grounded Social Simulation

AI 导读

研究者推出 ABSClaw,一个零代码智能体,可将自然语言请求编译为可执行的、基于真实数据的社会模拟,其人物、环境与交互网络均锚定调查、人口普查、地理空间数据和真实网络,并通过 26 个原子操作表达状态转移,还支持以生命周期作用域的技能扩展功能。

正文 · 原文

View PDF HTML (experimental)

Abstract:LLM-based artificial societies exhibit rich behavior but often lack scientific grounding: personas and environments are assumed, interaction networks are synthetic, and simulators are generated as free-form code, making results difficult to tie to real populations and sensitive to the backbone model. We argue that simulated worlds should be sampled from observed data, while simulation logic should be implemented by composing operations from a shared, task-independent vocabulary. In this paper, we introduce ABSClaw, a zero-code agent that compiles natural-language requests into executable, reality-grounded social simulations. ABSClaw grounds who acts, where they act, and with whom they interact in survey and census data, geospatial sources, and real networks. It expresses state transitions through 26 atomic operations. To support an open and extensible ecosystem, ABSClaw further allows capabilities to be added as lifecycle-scoped skills without modifying its core. Furthermore, we propose ABSBench, a benchmark of 193 real-world social-simulation tasks. On ABSBench, ABSClaw achieves the best overall performance among the evaluated social simulators. Three real-world case studies show that grounding personas, environments, and interaction networks each improves agreement with observed outcomes. With one runtime skill, ABSClaw executes 13 population-scale simulations, collectively involving 25 million agents. Together, these results demonstrate ABSClaw's real-world fidelity, extensibility, and scalability.
Subjects: Artificial Intelligence (cs.AI)
Cite as: arXiv:2611.24517 [cs.AI]
  (or arXiv:2611.24517v1 [cs.AI] for this version)
  https://doi.org/10.48550/arXiv.2611.24517

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Shobin He [view email]
[v1] Wed, 18 Nov 2026 14:37:48 UTC (1,412 KB)

来源:arXiv cs.AI · arxiv.org