Negotiating Comfort: Simulating Personality-Driven LLM Agents in Shared Residential Social Networks

TL;DR

This paper demonstrates how large language model-powered agents can simulate complex human social behaviors and decision-making in a shared residential environment, revealing how personality traits influence happiness and social bonds.

Contribution

It introduces a novel simulation framework using LLM-driven agents to model personality-driven social interactions and decision-making in a residential setting.

Findings

Positive personality traits correlate with higher happiness and stronger friendships.

Temperature preferences, assertiveness, and selflessness significantly influence happiness and decisions.

Simulated agents exhibit nuanced human-like social behaviors based on personality distributions.

Abstract

We use generative agents powered by large language models (LLMs) to simulate a social network in a shared residential building, driving the temperature decisions for a central heating system. Agents, divided into Family Members and Representatives, consider personal preferences, personal traits, connections, and weather conditions. Daily simulations involve family-level consensus followed by building-wide decisions among representatives. We tested three personality traits distributions (positive, mixed, and negative) and found that positive traits correlate with higher happiness and stronger friendships. Temperature preferences, assertiveness, and selflessness have a significant impact on happiness and decisions. This work demonstrates how LLM-driven agents can help simulate nuanced human behavior where complex real-life human simulations are difficult to set.