From Blueprint to Reality: Modeling and Applying Putnam's Social Capital Theory with LLM-based Multi-agent Simulations

2026-07-07

AI Summary

This study addresses the challenge of empirically replicating Putnam’s theory of social capital—particularly its collective action mechanisms—by proposing SocaSim, a novel framework that formally integrates Putnam’s theoretical constructs into a large language model (LLM)-based multi-agent system. SocaSim explicitly models social network evolution, trust dynamics, and norm diffusion within an interpretable simulation environment aligned with Putnam’s conceptual foundations. The framework successfully reproduces the macro-level societal patterns predicted by the theory, demonstrating human–agent consistency at the group level. Moreover, it uncovers micro-level causal pathways through iterative simulation rounds and enables counterfactual intervention analyses. Empirical validation in contexts such as smart eldercare confirms SocaSim’s explanatory power regarding adaptive societal challenges.

Abstract

Putnam's Social Capital Theory is a foundational framework for collective action and community prosperity. However, traditional empirical methods face practical limits on control and replication. Meanwhile, LLM-based social simulations are typically behavior-driven and lack theory-aligned environments for modeling Putnam's core propositions. To address these gaps, we introduce SocaSim, an LLM-based multi-agent simulation framework to study Putnam's Social Capital Theory from theoretical blueprint to simulated reality. Specifically, we build an environment integrating social network evolution, trust dynamics, and norm propagation, where agents engage in repeated collective-action experiments, and then apply the three dimensions to analyze adaptation challenges in smart elderly care. Our simulations reproduce Putnam's macro-level patterns and exhibit strong human-agent alignment at the group level. Unlike traditional methods, SocaSim traces micro-level causal pathways of social network, trust, and norms via round-by-round simulations and counterfactual interventions, enabling process-level interpretability. Taken together, these capabilities establish a research paradigm that leverages LLM agents to bridge social science and computer science.

Problem

• Social Capital Theory
• LLM-based simulation
• multi-agent system
• collective action
• theory-aligned environment

Innovation

• LLM-based multi-agent simulation
• Social Capital Theory
• Theory-aligned environment
• Process-level interpretability
• Counterfactual intervention