Simulating Society Requires Simulating Thought
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911228891234304 |
|---|---|
| author | Li, Chance Jiajie Wu, Jiayi Mo, Zhenze Qu, Ao Tang, Yuhan Zhao, Kaiya Ivy Gan, Yulu Fan, Jie Yu, Jiangbo Zhao, Jinhua Liang, Paul Alonso, Luis Larson, Kent |
| author_facet | Li, Chance Jiajie Wu, Jiayi Mo, Zhenze Qu, Ao Tang, Yuhan Zhao, Kaiya Ivy Gan, Yulu Fan, Jie Yu, Jiangbo Zhao, Jinhua Liang, Paul Alonso, Luis Larson, Kent |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_06958 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Simulating Society Requires Simulating Thought Li, Chance Jiajie Wu, Jiayi Mo, Zhenze Qu, Ao Tang, Yuhan Zhao, Kaiya Ivy Gan, Yulu Fan, Jie Yu, Jiangbo Zhao, Jinhua Liang, Paul Alonso, Luis Larson, Kent Computers and Society Artificial Intelligence Multiagent Systems 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. |
| title | Simulating Society Requires Simulating Thought |
| topic | Computers and Society Artificial Intelligence Multiagent Systems |
| url | https://arxiv.org/abs/2506.06958 |