模拟社会需要模拟思维
Simulating Society Requires Simulating Thought
AI总结：
针对LLM社会模拟缺乏认知基础的问题，提出GenMinds范式与RECAP基准，实现结构化信念与因果可追踪，推动从表面模仿转向思维模拟。
摘要：
我们认为，使用大型语言模型（LLM）模拟社会，需要的不仅仅是生成看似合理的行为；它要求具备认知基础的推理，这种推理是结构化的、可修正的且可追踪的。基于LLM的智能体越来越多地被用于模拟个体和群体行为，主要通过提示和监督微调实现。然而，当前的模拟仍停留在行为主义的“人口统计输入，行为输出”范式上，侧重于表面层面的合理性。因此，它们往往缺乏内部一致性、因果推理和信念可追溯性，使得它们在模拟人们如何推理、深思以及对干预做出反应方面不可靠。为解决这一问题，我们提出了一种概念性建模范式——生成心智（GenMinds），它借鉴认知科学来支持生成式智能体中的结构化信念表示。为了评估此类智能体，我们引入了RECAP（重构因果路径）框架，这是一个基准，旨在通过因果可追溯性、人口统计基础和干预一致性来评估推理保真度。这些贡献推动了更广泛的转变：从表面模仿转向生成式智能体，为社会模拟模拟思维而不仅仅是语言。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
