Simulating Generative Social Agents via Theory-Informed Workflow Design

TL;DR

This paper introduces a theory-informed framework for designing large language model-based social agents, enabling more realistic, adaptable, and context-aware social behaviors through structured modules inspired by Social Cognition Theory.

Contribution

It presents a systematic, modular design framework for social agents based on Social Cognition Theory, improving realism and generalization in social simulations.

Findings

Agents reproduce realistic human behavior patterns with up to 75% lower deviation from real data.

Removing key modules increases behavioral errors by 1.5 to 3.2 times.

The framework enhances agent adaptability and contextual appropriateness.

Abstract

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.