ABSClaw: From Invented Worlds to Reality-Grounded Social Simulation
The paper introduces ABSClaw, a zero-code agent that compiles natural-language requests into executable social simulations grounded in survey, census, geospatial, and real-network data. It expresses state transitions through 26 atomic operations and supports lifecycle-scoped skills without modifying its core. The authors also propose ABSBench, a benchmark of 193 real-world social-simulation tasks, and report that ABSClaw achieves the best overall performance among evaluated social simulators. Case studies indicate that grounding personas, environments, and interaction networks improves agreement with observed outcomes, and one runtime skill executes 13 population-scale simulations involving 25 million agents.
It offers a concrete framework and benchmark for making LLM-based social simulations more empirically grounded and reproducible.
Comments & Questions (0)
No comments yet
Be the first to comment!