Simulating Society Requires Simulating Thought

Chance Jiajie Li, Jiayi Wu, Zhenze Mo, Ao Qu, Yuhan Tang, Kaiya Ivy Zhao, Yulu Gan, Jie Fan, Jiangbo Yu, Jinhua Zhao, Paul Pu Liang, Luis Alberto Alonso Pastor, Kent Larson

Keywords: Social Simulation, Generative Agents, Human-like Reasoning, Cognitive Modeling, Bayesian Inference, Reasoning Fidelity, Causal Belief Graphs

TL;DR: We argue that simulating society with generative agents requires moving beyond behavioral mimicry toward cognitively grounded reasoning that is structured, revisable, and traceable.

Abstract:

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 current simulations remain grounded in a behaviorist “demographics in, behavior out” paradigm, focusing on surface-level plausibility. As a result, they often lack internal coherence, causal reasoning, and belief traceability—making them unreliable for modeling how people reason, deliberate, and 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.

Lay Summary: This position paper challenges the dominant paradigm in social simulation: modeling behavior based on demographics. We argue that to simulate society faithfully, AI must move beyond population-level correlations and instead align with how real individuals think and reason. By shifting the focus from outcomes to inner thought processes, we advocate for a more human-centered, cognitively grounded approach to simulating collective behavior.

Submission Number: 644