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

Jul 16, 2026

Upload by Riley

Putnam’s Social Capital Theory explains how social networks, trust, and norms shape collective action and community prosperity, but conventional empirical studies face limits in control, replication, and theory-aligned environments. LLM-based social simulations often remain behavior-driven and lack mechanisms tailored to Putnam’s propositions. The document presents SOCASIM, an LLM-based multi-agent simulation framework with network evolution, trust dynamics, and norm propagation. Round-by-round causal tracing and counterfactual interventions improve interpretability and support applications in smart elderly care.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages23

Reading Time58 min

Abstract

Introduction

Background: Social capital and collective action dilemmas

Limits of existing empirical and simulation paradigms

SOCASIM: theory-grounded LLM-based multi-agent framework

Progressive tasks: modeling and applying

Counterfactual evidence for trust as a causal lever

From Blueprint to Reality: Modeling and Applying Putnam’s Social Capital Theory with LLM-based Multi-agent Simulations Shiyi Ling1 , Zhi Zheng1 , Hui Zheng2 , Wenjun Xue3 , Feng Ye4 , Tong Xu1 1 State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China 2Anhui University 3North Automatic Control Technology Institute 4University of Science and Technology of China {shiyi.ling, awaken215, [yefengustc}@mail.ustc.edu.cn](yefengustc}@mail.ustc.edu.cn), {zhengzhi97, [tongxu}@ustc.edu.cn](tongxu}@ustc.edu.cn), [huizheng@ahu.edu.cn](huizheng@ahu.edu.cn), arXiv :2607 .06080v 1 [ cs .CL] 7 Jul 2026 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 LLMbased 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 roundby-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. 1 Introduction When an accident occurs, large anonymous crowds often freeze, each waiting for someone else to move first. In close-knit groups, help starts immediately because people are connected, trust one another, and expect to assist. This contrast shows how social network, trust, and norms shape a group’s ability to respond to common problems. Social Capital Theory, developed by Robert D. Putnam (Putnam et al., 1994 ; Putnam, 2000), captures these dynamics and explains why some communities overcome collective-action dilemmas while others do not. In social science, research on Putnam’s Social Figure 1: Comparison of existing research paradigms versus SOCASIM for Putnam’s Social Capital Theory. Capital Theory largely relies on conventional empirical methods that yield valuable insights yet have notable limits (Figure 1(a)) . Quantitative methods such as large-scale surveys (Durante et al., 2025) and Structural Equation Modeling (SEM) (Hoa, 2021 ; Sumi et al., 2025) require substantial time and resources, and face practical constraints on control and replication. In parallel, simulation-based approaches such as Agent-Based Modeling (ABM)(Shenk et al., 2019) allow controlled tests of assumptions, yet traditional rule-based agents rely on predefined and simple decision rules and struggle to capture the complexity of human reasoning, emotion, and context-dependent behavior. Recently, advances in large language models (LLMs) have enabled the simulation of human-like intelligence (Friha et al., 2024 ; Wang et al., 2025a), prompting growing interest in LLM-based agents for social simulation (Piao et al., 2026 ; Yang et al., 2025) . However, existing approaches are largely behavior-driven rather than theory-driven (Figure 1(b)): they typically test whether agents exhibit plausible or human-like behavior on specific tasks (Zhao et al., 2024 ; Jia et al., 2025 ; Xie et al., 2024), but rarely construct environments aligned with core theoretical propositions. Furthermore, current frameworks seldom provide reproducible, controllable settings fo

FAQs

What problem does the document address regarding Putnam’s Social Capital Theory studies?

Traditional empirical methods have limits in control, replication, and theory-aligned modeling, while existing LLM simulations are mostly behavior-driven and do not construct environments aligned with Putnam’s core propositions.

What is SOCASIM and what mechanisms does it integrate?

SOCASIM is an LLM-based multi-agent simulation framework that integrates dynamic social network evolution, trust adaptation, and norm diffusion so agents can run repeated collective-action experiments across rounds.

How does the framework support interpretability and causal analysis?

SOCASIM traces micro-level causal pathways for social networks, trust, and norms through round-by-round simulations and counterfactual interventions, enabling process-level interpretability beyond traditional outcomes-only analysis.

Jul 16, 2026

Upload by Riley