cs.AINov 18, 2026

ABSClaw: From Invented Worlds to Reality-Grounded Social Simulation

Authors: Shaobin He, Yan Gao, Quan Zheng, Zhenyang Lin, Zhen Liu, Jiyan He, Shuxin Zheng

Organizations: Tianjin University · Zhongguancun Academy · Zhongguancun Institute of Artificial Intelligence · Beijing Normal University

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.

Figures & tables

Explore similar work

CardsList
  1. The Silicon Society\textit{Silicon Society} Cookbook: Design Space of LLM-based Social Simulations

    Apr 30, 2026Aurélien Bück-Kaeffer, Sneheel Sarangi, Maximilian Puelma Touzel +3Multi-Agent LLM SystemsHuman Behavior Simulation

  2. SOCIA-∇\nabla: Textual Gradient Meets Multi-Agent Orchestration for Automated Simulator Generation

    May 17, 2025Yuncheng Hua, Sion Weatherhead, Mehdi Jafari +2Large Language Model-Based SimulationCode Generation

  3. AgoraSim: A Hybrid Agent-Based Modeling Framework

    Jul 7, 2026Chung-Chi ChenHuman Behavior SimulationLLM Agent Orchestration