Simulating Generative Social Agents via Theory-Informed Workflow Design
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918122946035712 |
|---|---|
| author | Yan, Yuwei Piao, Jinghua Lan, Xiaochong Shao, Chenyang Hui, Pan Li, Yong |
| author_facet | Yan, Yuwei Piao, Jinghua Lan, Xiaochong Shao, Chenyang Hui, Pan Li, Yong |
| contents | Recent advances in large language models have demonstrated strong reasoning and role-playing capabilities, opening new opportunities for agent-based social simulations. However, most existing agents' implementations are scenario-tailored, without a unified framework to guide the design. This lack of a general social agent limits their ability to generalize across different social contexts and to produce consistent, realistic behaviors. To address this challenge, we propose a theory-informed framework that provides a systematic design process for LLM-based social agents. Our framework is grounded in principles from Social Cognition Theory and introduces three key modules: motivation, action planning, and learning. These modules jointly enable agents to reason about their goals, plan coherent actions, and adapt their behavior over time, leading to more flexible and contextually appropriate responses. Comprehensive experiments demonstrate that our theory-driven agents reproduce realistic human behavior patterns under complex conditions, achieving up to 75% lower deviation from real-world behavioral data across multiple fidelity metrics compared to classical generative baselines. Ablation studies further show that removing motivation, planning, or learning modules increases errors by 1.5 to 3.2 times, confirming their distinct and essential contributions to generating realistic and coherent social behaviors. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_08726 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Simulating Generative Social Agents via Theory-Informed Workflow Design Yan, Yuwei Piao, Jinghua Lan, Xiaochong Shao, Chenyang Hui, Pan Li, Yong Artificial Intelligence Computers and Society Recent advances in large language models have demonstrated strong reasoning and role-playing capabilities, opening new opportunities for agent-based social simulations. However, most existing agents' implementations are scenario-tailored, without a unified framework to guide the design. This lack of a general social agent limits their ability to generalize across different social contexts and to produce consistent, realistic behaviors. To address this challenge, we propose a theory-informed framework that provides a systematic design process for LLM-based social agents. Our framework is grounded in principles from Social Cognition Theory and introduces three key modules: motivation, action planning, and learning. These modules jointly enable agents to reason about their goals, plan coherent actions, and adapt their behavior over time, leading to more flexible and contextually appropriate responses. Comprehensive experiments demonstrate that our theory-driven agents reproduce realistic human behavior patterns under complex conditions, achieving up to 75% lower deviation from real-world behavioral data across multiple fidelity metrics compared to classical generative baselines. Ablation studies further show that removing motivation, planning, or learning modules increases errors by 1.5 to 3.2 times, confirming their distinct and essential contributions to generating realistic and coherent social behaviors. |
| title | Simulating Generative Social Agents via Theory-Informed Workflow Design |
| topic | Artificial Intelligence Computers and Society |
| url | https://arxiv.org/abs/2508.08726 |