Simulating society with large language models (LLMs), we argue, requires more than generating plausible behavior -- it demands cognitively grounded reasoning that is structured, revisable, and traceable. LLM-based agents are increasingly used to emulate individual and group behavior -- primarily through prompting and supervised fine-tuning. Yet they often lack internal coherence, causal reasoning, and belief traceability -- making them unreliable for analyzing how people reason, deliberate, or respond to interventions.To address this, we present a conceptual modeling paradigm, Generative Minds (GenMinds), which draws from cognitive science to support structured belief representations in generative agents. To evaluate such agents, we introduce the RECAP (REconstructing CAusal Paths) framework, a benchmark designed to assess reasoning fidelity via causal traceability, demographic grounding, and intervention consistency. These contributions advance a broader shift: from surface-level mimicry to generative agents that simulate thought -- not just language -- for social simulations.
View on arXiv@article{li2025_2506.06958,
title={ Position: Simulating Society Requires Simulating Thought },
author={ Chance Jiajie Li and Jiayi Wu and Zhenze Mo and Ao Qu and Yuhan Tang and Kaiya Ivy Zhao and Yulu Gan and Jie Fan and Jiangbo Yu and Jinhua Zhao and Paul Liang and Luis Alonso and Kent Larson },
journal={arXiv preprint arXiv:2506.06958},
year={ 2025 }
}